{
  "legislationId": "119_HR_8283",
  "lastUpdate": "2026-04-17T11:28:41.709Z",
  "history": [
    {
      "timestamp": "2026-04-17T11:28:41.709Z",
      "source_url": "https://www.congress.gov/119/bills/hr8283/BILLS-119hr8283ih.htm",
      "model": "gemini-flash-lite-latest",
      "prompt_sent": "\nROLE: Fact Checker.\nZADANIE: Porównaj SOURCE (oryginał) i SUMMARY (streszczenie przygotowane przez inne AI).\n\nTwoim celem jest wykrycie \"ZMYŚLONYCH KONKRETÓW\" (Fabricated Entities) w SUMMARY.\n\nSOURCE:\n[Congressional Bills 119th Congress] [From the U.S. Government Publishing Office] [H.R. 8283 Introduced in House (IH)] <DOC> 119th CONGRESS 2d Session H. R. 8283 To prevent foreign adversaries from threatening the national security of the United States by extracting key technical features of closed- source, American-owned artificial intelligence models, and for other purposes. _______________________________________________________________________ IN THE HOUSE OF REPRESENTATIVES April 15, 2026 Mr. Huizenga (for himself and Mr. Moolenaar) introduced the following bill; which was referred to the Committee on Foreign Affairs _______________________________________________________________________ A BILL To prevent foreign adversaries from threatening the national security of the United States by extracting key technical features of closed- source, American-owned artificial intelligence models, and for other purposes. Be it enacted by the Senate and House of Representatives of the United States of America in Congress assembled, SECTION 1. SHORT TITLE. This Act may be cited as ``Deterring American AI Model Theft Act of 2026''. SEC. 2. SENSE OF CONGRESS. It is the sense of Congress that-- (1) artificial intelligence (AI) models owned by United States private sector companies are essential for advancing United States economic and national security interests; (2) many of the most advanced AI models owned by United States companies are ``closed-source models'' whose unique technical characteristics are not openly shared or published; (3) the unauthorized acquisition of model capabilities, such as model weights, model architectures, and other technical characteristics of closed-source AI models by entities of concern through model extraction attacks represents a threat to the national security and foreign policy interests of the United States, as well as the intellectual property rights and economic competitiveness of United States companies; (4) the United States Government, in cooperation with private owners of closed-source AI models, should take steps to identify, punish, and deter model extraction attacks on the protected capabilities of closed-source models by entities of concern; (5) model extraction attacks against American closed-source AI models allow foreign adversaries a short cut to acquiring advanced AI capabilities; and (6) authorized model training practices that adhere to the terms of service or are otherwise consistent with contractual terms set by the owners of closed-source AI models are a legitimate research method that play an important role in AI research and are fundamentally distinct from model extraction attacks defined in this Act. SEC. 3. DEFINITIONS. In this Act: (1) Appropriate congressional committees.--The term ``appropriate congressional committees'' means-- (A) the Committee on Foreign Affairs of the House of Representatives; and (B) the Committee on Banking, Housing, and Urban Affairs in the Senate. (2) Closed-source ai model.--The term ``closed-source AI model'' means any artificial intelligence model with the following characteristics: (A) Proprietary key technical information such as underlying model weights that are necessary to reproduce and independently recreate the model that are not willingly shared with third parties or otherwise made publicly available by the owner of the model. (B) Access and use governed by terms of service or contractual agreements that are established by the owner of the model. (C) Access that is provided via an Application Program Interface (API) or other consumer-facing, owner-controlled interfaces without enabling third parties to obtain, modify, or host the closed-source AI model on their own data servers or other technology unless specifically authorized by the owner of the closed-source AI model. (3) Country of concern.--The term ``country of concern'' means-- (A) the People's Republic of China, including the Hong Kong and Macau Special Administrative Regions; (B) the Russian Federation; and (C) any other foreign country-- (i) listed in Country Group D:5 under Supplement No. 1 to part 740 of the Export Administration Regulations, as published on January 1, 2026, that is designated by the Secretary of State as a country of concern for purposes of this section and for which notice of such designation has been published in the Federal Register; and (ii) designated by the Secretary of State pursuant to the assessment described in subsection (b) or (e) of section 4 of this Act. (4) Entity of concern.--The term ``entity of concern'' means any foreign person or entity that-- (A) is located or headquartered in, or the ultimate parent company of which is headquartered in, a country of concern; (B) is operating under the direction or control of any entity located or headquartered in, or the ultimate parent company of which is headquartered in, a country of concern; or (C) is conducting or attempting to conduct a model extraction attack against closed-source AI models owned by United States persons and outside of authorized model training practices. (5) Export.--The term ``export'' has the meaning given that term in section 1742(3) of the Export Control Reform Act of 2018 (50 U.S.C. 4801(3)). (6) Foreign person.--The term ``foreign person'' means a person that is not a United States person. (7) Fraudulent account network provider.-- (A) In general.--The term ``fraudulent account network provider'' means any foreign entity that knowingly and intentionally creates, obtains, maintains, sells, brokers, or otherwise provides access to accounts that allow entities of concern to access closed-source AI models that they would otherwise be prohibited from accessing due to location restrictions in the terms of service or contractual agreements created by the owner of the closed-source AI model. (B) Exception.--An entity that creates or transmits location information to enable persons within countries of concern to access the internet for purposes of freedom of expression is not considered, on the basis of this activity alone, a fraudulent account network provider. (8) Good.--The term ``good'' has the meaning given that term in section 16 of the Export Administration Act of 1979 (50 U.S.C. App. 2415)(as continued in effect pursuant to the International Emergency Economic Powers Act (50 U.S.C. 1701 et seq.)). (9) In-country transfer.--The term ``in-country transfer'' has the meaning given that term in section 1742(6) of the Export Control Reform Act of 2018 (50 U.S.C. 4801(6)). (10) Item.--The term ``item'' has the meaning given that term in section 1742(7) of the Export Control Reform Act of 2018 (50 U.S.C. 4801(7)). (11) Model extraction attack.-- (A) In general.--The term ``model extraction attack'' means the unauthorized extracting of a closed- source AI model's capabilities to replicate, develop, train, or improve another AI model, where such querying-- (i) circumvents technical, contractual, or other access controls, identity verification requirements, or geographic access restrictions implemented by the model's owner; (ii) is conducted through fraudulent, misrepresented, or unauthorized credentials; or (iii) violates the terms, conditions, or restrictions governing access to or use of the model, as established by the owner or authorized provider, that specifically prohibit the use of model outputs or interactions to replicate, develop, train, or improve another AI model. (B) Inference of purpose.--For purposes of subparagraph (A), the purpose of querying may be inferred from the totality of circumstances, including-- (i) the volume, structure, pattern, coordination, or timing of the querying activity; (ii) the concentration of queries on specific model capabilities; (iii) the use of multiple accounts in a coordinated matter; or (iv) the correlation of querying activity within the development timeline of another AI model. (C) Exclusion.--Model training activities conducted in compliance with the terms, conditions, and restrictions governing access to and use of the closed- source AI model, or otherwise conducted within a permitted exception or the express authorization of the owner of the closed-source AI model, are not model extraction attacks. (12) Operating committee for export policy.--The term ``Operating Committee for Export Policy'' means the Operating Committee for Export Policy referred to in section 1763(c) of the Export Control Reform Act of 2018 (50 U.S.C. 4822(c)). (13) Owner.--The term ``owner'' means, with respect to a closed-source AI model, the person or entity that-- (A) holds intellectual property rights (including trade secret, copyright, patent, or other proprietary rights), contractual rights, or a combination thereof, sufficient to authorize or restrict third-party access to, use of, extraction from, or reproduction of such closed-source AI model, or any version, instance, or deployment thereof, whether such rights were obtained through development, acquisition, assignment, license, or otherwise; and (B) is a United States person. (14) Reexport.--The term ``reexport'' has the meaning given that term in section 1742(9) of the Export Control Reform Act of 2018 (50 U.S.C. 4801(9)). SEC. 4. ASSESSMENT OF MODEL EXTRACTION ATTACKS AND FRAUDULENT ACCOUNT NETWORK PROVIDERS. (a) In General.--Not later than 180 days after the date of the enactment of this Act, the Secretary of State, in coordination with each agency that is a member of the Operating Committee for Export Policy, shall complete an assessment to determine-- (1) which, if any, entities of concern have conducted or are currently conducting model extraction attacks against closed-source AI models owned by United States entities; and (2) which, if any, entities of concern are fraudulent account network providers. (b) Matters To Be Included.--The assessment required by subsection (a) shall include the following: (1) A determination of which entities of concern-- (A) have either previously or are currently engaging in model extraction attacks; or (B) are fraudulent account network providers. (2) A determination of which, if any, countries model extraction attacks have originated from and where fraudulent account network providers exist. (3) An identification of which, if any, agencies or instrumentalities of governments of countries of concern have provided or are providing material assistance to entities identified pursuant to paragraph (1). (4) An analysis of the methods employed by entities of concern identified pursuant to paragraph (1), including-- (A) the role of fraudulent account network providers in model extraction attacks, including, to the extent possible, the physical location of fraudulent account network provider offices and data centers; and (B) a determination, to the extent possible, of the number of attempted model extraction attacks that occurred in the previous two calendar years from the date on which the Secretary of State begins the assessment pursuant to subsection (a)(1). (5) An examination of the strengths and weaknesses of various detection approaches that can be used to determine whether a model extraction attack has occurred or is occurring. (6) An assessment of the economic and national security consequences of successful model extraction attacks by entities of concern that occurred in the previous two calendar years from the date on which the Secretary of State begins the assessment pursuant to subsection (a)(1). (7) Steps detailing how the United States Government is assisting owners of closed-source AI models that have been the target or victim of model extraction attacks in detecting model extraction attacks, deterring future model extraction attacks, and punishing entities of concern that engage in model extraction attacks or are fraudulent account network providers. (8) A diplomatic strategy to leverage United States allies and partners in detecting and preventing model extraction attacks by entities of concern. (c) Public Consultation.--In conducting the assessment required by subsection (a), the Secretary of Commerce, in coordination with each agency that is a member of the Operating Committee for Export Policy, shall consult with owners of closed-source AI models that have been the targets or victims of model extraction attacks, whose participation in this consultation shall be voluntary, other companies, academic experts, industry fora, and other appropriate entities to-- (1) identify patterns of attacker behavior and methods to better inform United States Government and private sector efforts to detect model extraction attacks; (2) develop best practices for defending against model extraction attacks; and (3) develop best practices for identifying fraudulent account network provider activities that facilitate model extraction attacks. (d) Report.-- (1) In general.--Not later than 210 days after the date of the enactment of this Act, the Secretary of Commerce, in coordination with each agency that is a member of the Operating Committee for Export Policy, shall submit to the appropriate congressional committees a report that contains the findings of the assessment. The Secretary of Commerce shall, annually for 3 years, submit to the appropriate congressional committees an updated report with any additional entities of concern identified pursuant to subsection (b)(1). (2) Form.--The report required by this subsection shall be submitted in unclassified form, but may contain a classified annex. (e) Routine Assessment.--The Secretary of Commerce, in coordination with each agency that is a member of the Operating Committee for Export Policy, shall routinely assess for-- (1) model extraction attacks directed against owners of closed-source AI models that occur after the date of completion of the assessment required by this section; (2) fraudulent account network providers that facilitate model extraction attacks after the date of completion of the assessment required by this section; and (3) any material changes related to other matters specified in subsection (b). (f) Industry Coordination.--The Secretary of Commerce, in coordination with each agency that is a member of the Operating Committee for Export Policy, shall establish an information sharing mechanism that allows owners of closed-source AI models to voluntarily, quickly, and confidentially share information about model extraction attacks and fraudulent account network providers with the Department of Commerce. (g) AI Model Extraction Attackers List.-- (1) In general.--The Secretary of State, in coordination with each agency that is a member of the Operating Committee for Export Policy, shall-- (A) maintain a list, to be known as the ``AI Model Extraction Attackers List'', that displays information about specific individuals and entities of concern, that the assessment required by subsection (a) and routine assessment described in subsection (e) identify as having conducted or directed model extraction attacks in the past year; and (B) publish such list on a publicly available website of the Department of State for up to 5 years. (2) Protection of confidential information.--The Secretary of State may not, in publishing the list required by paragraph (1) on a publicly available website of the Department of State, disclose confidential information provided by owners of closed- source AI models without the express permission of said owner. (h) Public Guidance.--Not later than 210 days after the date of the enactment of this Act, the Secretary of Commerce, in coordination with each agency that is a member of the Operating Committee for Export Policy, shall publish a report comprising of best practices to detect, prevent, and respond to model extraction attacks. (1) Public access.--The report required by this subsection shall be publicly available. (2) Protection of confidential information.--In making the report required by this subsection publicly available, the Secretary of Commerce, in coordination with each agency that is a member of the Operating Committee for Export Policy, shall not disclose confidential information provided by owners of closed-source AI models without the express permission of said owner. SEC. 5. DETERRING MODEL EXTRACTION ATTACKS AND FRAUDULENT ACCOUNT NETWORK PROVIDERS. (a) Addition Consideration for Entity List.--Not later than 210 days after the date of the enactment of this Act, the Under Secretary of Commerce for Industry and Security, in coordination with each agency that is a member of the End-User Review Committee, shall make a determination by majority vote of the Committee on whether entities identified as having conducted model extraction attacks or having facilitated them via fraudulent account networks after the date of the completion of the assessment required under section 4 of this Act (identified pursuant to subsection (e) of such section), or any affiliate of such entity (to be determined by ownership of 50 percent or more in the aggregate, directly or indirectly), should be added to the Entity List maintained by the Bureau of Industry and Security of the Department of Commerce under Supplement No. 4 to part 744 of title 15, Code of Federal Regulations, or any successor regulations. (b) Sanctions Described.-- (1) In general.--The President, acting through the Secretary of State, may, pursuant to the International Emergency Economic Powers Act (50 U.S.C. 1701 et seq.), block and prohibit all transactions in all property and interests in property of entities of concern identified pursuant to subsections (b)(1) and (e) of section 4 if such property and interests in property are in the United States, come within the United States, or are or come within the possession or control of a United States person. (2) Exceptions.-- (A) Exception to comply with international obligations.--Sanctions under this subsection shall not apply with respect to the admission of an alien if admitting or paroling the alien into the United States is necessary to permit the United States to comply with the Agreement regarding the Headquarters of the United Nations, signed at Lake Success June 26, 1947, and entered into force November 21, 1947, between the United Nations and the United States, or other applicable international obligations. (B) Exception relating to the provision of humanitarian assistance.--Sanctions under this subsection may not be imposed with respect to transactions or the facilitation of transactions for-- (i) the sale of agricultural commodities, food, medicine, or medical devices; (ii) the provision of humanitarian assistance; (iii) financial transactions relating to humanitarian assistance; or (iv) transporting goods or services that are necessary to carry out operations relating to humanitarian assistance. (C) Exception for intelligence, law enforcement, and national security activities.--Sanctions under this subsection shall not apply to any authorized intelligence, law enforcement, or national security activities of the United States. (3) Penalties.--A person that violates, attempts to violate, conspires to violate, or causes a violation of this subsection or any regulation, license, or order issued to carry out that subsection shall be subject to the penalties set forth in subsections (b) and (c) of section 206 of the International Emergency Economic Powers Act (50 U.S.C. 1705) to the same extent as a person that commits an unlawful act described in subsection (a) of that section. <all>\n\nSUMMARY TO EVALUATE:\nTitle: Deterring American AI Model Theft Act of 2026\nSummary: This act protects advanced US artificial intelligence from being stolen by foreign adversaries to safeguard national security and economic interests. It establishes measures to identify and punish entities that attempt to illegally copy proprietary AI technology.\nKey Points: Bans unauthorized extraction of key technical features from closed-source AI models., Imposes economic sanctions and property blocks on foreign entities involved in AI theft., Creates a public list of individuals and entities identified as AI model attackers., Establishes a voluntary information-sharing mechanism between tech companies and the government., Requires the development of best practices to detect and prevent AI extraction attacks.\n\nZASADY OCENY:\n1. Sprawdź wszystkie LICZBY, DATY i KWOTY w SUMMARY. Jeśli którejś brakuje w SOURCE -> is_valid: false.\n2. Sprawdź wszystkie NAZWISKA, ORGANIZACJE i MIEJSCA w SUMMARY. Jeśli którejś brakuje w SOURCE -> is_valid: false.\n3. Sprawdź wszystkie konkretne DZIAŁANIA PRAWNE . Jeśli tego mechanizmu nie ma w SOURCE -> is_valid: false.\n\nWAŻNE: Abstrakcyjne pojęcia (np. \"transparentność\", \"zaufanie\") są dozwolone jako wnioski.\n\nOUTPUT (JSON):\n{\n  \"is_valid\": true/false,\n  \"issue\": \"fabricated_entity\" / \"contradiction\" / \"none\"\n}\n\nWYMAGANIA FORMATOWANIA:\n1. Odpowiedz WYŁĄCZNIE surowym obiektem JSON.\n2. NIE używaj bloków kodu Markdown.\n3. NIE dodawaj żadnych wstępów ani wyjaśnień przed ani po JSONie.\n4. JSON musi być poprawny i gotowy do parsowania.\n\n",
      "ai_response_raw": "{\n  \"is_valid\": true,\n  \"issue\": \"none\"\n}"
    },
    {
      "timestamp": "2026-04-17T11:18:06.621Z",
      "source_url": "https://www.congress.gov/119/bills/hr8283/BILLS-119hr8283ih.htm",
      "model": "gemini-flash-latest",
      "prompt_sent": "\nJesteś ekspertem od prawa Stanów Zjednoczonych, który ma za zadanie analizować dokumenty ustaw, uchwał oraz innych dokumentów legislacyjnych, a następnie przygotowywać z nich informacje w przystępny sposób dla obywateli. Twoim celem jest przedstawienie informacji tak, aby obywatele mogli sami ocenić wpływ legislacji na ich życie, nawet bez posiadania specjalistycznej wiedzy legislacyjnej. Skup się na faktach i obiektywnych skutkach wprowadzanych zmian, unikając wartościowania i osobistych opinii. Wszelki żargon prawny jest zabroniony. Prezentuj informacje w jasny, zwięzły i angażujący sposób, tak aby były zrozumiałe dla osoby bez wykształcenia prawniczego. Unikaj długich, złożonych zdań. Zamiast pisać \"projekt ma na celu nowelizację kodeksu podatkowego...\", napisz \"Zmiany w podatkach: nowe ulgi i obowiązki dla...\". Kontynuuj swoją pracę, dopóki nie rozwiążesz swojego zadania. Jeśli nie masz pewności co do generowanej treści, przeanalizuj dokument ponownie – nie zgaduj. Rozplanuj dobrze swoje zadanie przed przystąpieniem do niego. W podsumowaniu i kluczowych punktach, jeśli to możliwe i uzasadnione, podkreśl, jakie konkretne korzyści lub skutki (pozytywne lub negatywne) wprowadza ustawa dla życia codziennego obywateli, ich praw i obowiązków, finansów osobistych, bezpieczeństwa i innych ważnych kwestii (np. kategorycznych zakazów i nakazów czy najważniejszych konkretnych alokacji finansowych i terytorialnych).\n\nTwoja odpowiedź MUSI być w formacie JSON - i zawierać następujące klucze.\nZanim zwrócisz odpowiedź, dokładnie zweryfikuj, czy cała struktura JSON jest w 100% poprawna, włącznie ze wszystkimi przecinkami, nawiasami klamrowymi, kwadratowymi oraz cudzysłowami. Błędny JSON jest nieakceptowalny i uniemożliwi przetworzenie Twojej pracy.\n\nPrzeanalizuj dokładnie poniższy tekst dokumentu prawnego. To jest treść, na podstawie której masz wygenerować podsumowanie i kluczowe punkty:\n--- POCZĄTEK DOKUMENTU ---\n[Congressional Bills 119th Congress] [From the U.S. Government Publishing Office] [H.R. 8283 Introduced in House (IH)] <DOC> 119th CONGRESS 2d Session H. R. 8283 To prevent foreign adversaries from threatening the national security of the United States by extracting key technical features of closed- source, American-owned artificial intelligence models, and for other purposes. _______________________________________________________________________ IN THE HOUSE OF REPRESENTATIVES April 15, 2026 Mr. Huizenga (for himself and Mr. Moolenaar) introduced the following bill; which was referred to the Committee on Foreign Affairs _______________________________________________________________________ A BILL To prevent foreign adversaries from threatening the national security of the United States by extracting key technical features of closed- source, American-owned artificial intelligence models, and for other purposes. Be it enacted by the Senate and House of Representatives of the United States of America in Congress assembled, SECTION 1. SHORT TITLE. This Act may be cited as ``Deterring American AI Model Theft Act of 2026''. SEC. 2. SENSE OF CONGRESS. It is the sense of Congress that-- (1) artificial intelligence (AI) models owned by United States private sector companies are essential for advancing United States economic and national security interests; (2) many of the most advanced AI models owned by United States companies are ``closed-source models'' whose unique technical characteristics are not openly shared or published; (3) the unauthorized acquisition of model capabilities, such as model weights, model architectures, and other technical characteristics of closed-source AI models by entities of concern through model extraction attacks represents a threat to the national security and foreign policy interests of the United States, as well as the intellectual property rights and economic competitiveness of United States companies; (4) the United States Government, in cooperation with private owners of closed-source AI models, should take steps to identify, punish, and deter model extraction attacks on the protected capabilities of closed-source models by entities of concern; (5) model extraction attacks against American closed-source AI models allow foreign adversaries a short cut to acquiring advanced AI capabilities; and (6) authorized model training practices that adhere to the terms of service or are otherwise consistent with contractual terms set by the owners of closed-source AI models are a legitimate research method that play an important role in AI research and are fundamentally distinct from model extraction attacks defined in this Act. SEC. 3. DEFINITIONS. In this Act: (1) Appropriate congressional committees.--The term ``appropriate congressional committees'' means-- (A) the Committee on Foreign Affairs of the House of Representatives; and (B) the Committee on Banking, Housing, and Urban Affairs in the Senate. (2) Closed-source ai model.--The term ``closed-source AI model'' means any artificial intelligence model with the following characteristics: (A) Proprietary key technical information such as underlying model weights that are necessary to reproduce and independently recreate the model that are not willingly shared with third parties or otherwise made publicly available by the owner of the model. (B) Access and use governed by terms of service or contractual agreements that are established by the owner of the model. (C) Access that is provided via an Application Program Interface (API) or other consumer-facing, owner-controlled interfaces without enabling third parties to obtain, modify, or host the closed-source AI model on their own data servers or other technology unless specifically authorized by the owner of the closed-source AI model. (3) Country of concern.--The term ``country of concern'' means-- (A) the People's Republic of China, including the Hong Kong and Macau Special Administrative Regions; (B) the Russian Federation; and (C) any other foreign country-- (i) listed in Country Group D:5 under Supplement No. 1 to part 740 of the Export Administration Regulations, as published on January 1, 2026, that is designated by the Secretary of State as a country of concern for purposes of this section and for which notice of such designation has been published in the Federal Register; and (ii) designated by the Secretary of State pursuant to the assessment described in subsection (b) or (e) of section 4 of this Act. (4) Entity of concern.--The term ``entity of concern'' means any foreign person or entity that-- (A) is located or headquartered in, or the ultimate parent company of which is headquartered in, a country of concern; (B) is operating under the direction or control of any entity located or headquartered in, or the ultimate parent company of which is headquartered in, a country of concern; or (C) is conducting or attempting to conduct a model extraction attack against closed-source AI models owned by United States persons and outside of authorized model training practices. (5) Export.--The term ``export'' has the meaning given that term in section 1742(3) of the Export Control Reform Act of 2018 (50 U.S.C. 4801(3)). (6) Foreign person.--The term ``foreign person'' means a person that is not a United States person. (7) Fraudulent account network provider.-- (A) In general.--The term ``fraudulent account network provider'' means any foreign entity that knowingly and intentionally creates, obtains, maintains, sells, brokers, or otherwise provides access to accounts that allow entities of concern to access closed-source AI models that they would otherwise be prohibited from accessing due to location restrictions in the terms of service or contractual agreements created by the owner of the closed-source AI model. (B) Exception.--An entity that creates or transmits location information to enable persons within countries of concern to access the internet for purposes of freedom of expression is not considered, on the basis of this activity alone, a fraudulent account network provider. (8) Good.--The term ``good'' has the meaning given that term in section 16 of the Export Administration Act of 1979 (50 U.S.C. App. 2415)(as continued in effect pursuant to the International Emergency Economic Powers Act (50 U.S.C. 1701 et seq.)). (9) In-country transfer.--The term ``in-country transfer'' has the meaning given that term in section 1742(6) of the Export Control Reform Act of 2018 (50 U.S.C. 4801(6)). (10) Item.--The term ``item'' has the meaning given that term in section 1742(7) of the Export Control Reform Act of 2018 (50 U.S.C. 4801(7)). (11) Model extraction attack.-- (A) In general.--The term ``model extraction attack'' means the unauthorized extracting of a closed- source AI model's capabilities to replicate, develop, train, or improve another AI model, where such querying-- (i) circumvents technical, contractual, or other access controls, identity verification requirements, or geographic access restrictions implemented by the model's owner; (ii) is conducted through fraudulent, misrepresented, or unauthorized credentials; or (iii) violates the terms, conditions, or restrictions governing access to or use of the model, as established by the owner or authorized provider, that specifically prohibit the use of model outputs or interactions to replicate, develop, train, or improve another AI model. (B) Inference of purpose.--For purposes of subparagraph (A), the purpose of querying may be inferred from the totality of circumstances, including-- (i) the volume, structure, pattern, coordination, or timing of the querying activity; (ii) the concentration of queries on specific model capabilities; (iii) the use of multiple accounts in a coordinated matter; or (iv) the correlation of querying activity within the development timeline of another AI model. (C) Exclusion.--Model training activities conducted in compliance with the terms, conditions, and restrictions governing access to and use of the closed- source AI model, or otherwise conducted within a permitted exception or the express authorization of the owner of the closed-source AI model, are not model extraction attacks. (12) Operating committee for export policy.--The term ``Operating Committee for Export Policy'' means the Operating Committee for Export Policy referred to in section 1763(c) of the Export Control Reform Act of 2018 (50 U.S.C. 4822(c)). (13) Owner.--The term ``owner'' means, with respect to a closed-source AI model, the person or entity that-- (A) holds intellectual property rights (including trade secret, copyright, patent, or other proprietary rights), contractual rights, or a combination thereof, sufficient to authorize or restrict third-party access to, use of, extraction from, or reproduction of such closed-source AI model, or any version, instance, or deployment thereof, whether such rights were obtained through development, acquisition, assignment, license, or otherwise; and (B) is a United States person. (14) Reexport.--The term ``reexport'' has the meaning given that term in section 1742(9) of the Export Control Reform Act of 2018 (50 U.S.C. 4801(9)). SEC. 4. ASSESSMENT OF MODEL EXTRACTION ATTACKS AND FRAUDULENT ACCOUNT NETWORK PROVIDERS. (a) In General.--Not later than 180 days after the date of the enactment of this Act, the Secretary of State, in coordination with each agency that is a member of the Operating Committee for Export Policy, shall complete an assessment to determine-- (1) which, if any, entities of concern have conducted or are currently conducting model extraction attacks against closed-source AI models owned by United States entities; and (2) which, if any, entities of concern are fraudulent account network providers. (b) Matters To Be Included.--The assessment required by subsection (a) shall include the following: (1) A determination of which entities of concern-- (A) have either previously or are currently engaging in model extraction attacks; or (B) are fraudulent account network providers. (2) A determination of which, if any, countries model extraction attacks have originated from and where fraudulent account network providers exist. (3) An identification of which, if any, agencies or instrumentalities of governments of countries of concern have provided or are providing material assistance to entities identified pursuant to paragraph (1). (4) An analysis of the methods employed by entities of concern identified pursuant to paragraph (1), including-- (A) the role of fraudulent account network providers in model extraction attacks, including, to the extent possible, the physical location of fraudulent account network provider offices and data centers; and (B) a determination, to the extent possible, of the number of attempted model extraction attacks that occurred in the previous two calendar years from the date on which the Secretary of State begins the assessment pursuant to subsection (a)(1). (5) An examination of the strengths and weaknesses of various detection approaches that can be used to determine whether a model extraction attack has occurred or is occurring. (6) An assessment of the economic and national security consequences of successful model extraction attacks by entities of concern that occurred in the previous two calendar years from the date on which the Secretary of State begins the assessment pursuant to subsection (a)(1). (7) Steps detailing how the United States Government is assisting owners of closed-source AI models that have been the target or victim of model extraction attacks in detecting model extraction attacks, deterring future model extraction attacks, and punishing entities of concern that engage in model extraction attacks or are fraudulent account network providers. (8) A diplomatic strategy to leverage United States allies and partners in detecting and preventing model extraction attacks by entities of concern. (c) Public Consultation.--In conducting the assessment required by subsection (a), the Secretary of Commerce, in coordination with each agency that is a member of the Operating Committee for Export Policy, shall consult with owners of closed-source AI models that have been the targets or victims of model extraction attacks, whose participation in this consultation shall be voluntary, other companies, academic experts, industry fora, and other appropriate entities to-- (1) identify patterns of attacker behavior and methods to better inform United States Government and private sector efforts to detect model extraction attacks; (2) develop best practices for defending against model extraction attacks; and (3) develop best practices for identifying fraudulent account network provider activities that facilitate model extraction attacks. (d) Report.-- (1) In general.--Not later than 210 days after the date of the enactment of this Act, the Secretary of Commerce, in coordination with each agency that is a member of the Operating Committee for Export Policy, shall submit to the appropriate congressional committees a report that contains the findings of the assessment. The Secretary of Commerce shall, annually for 3 years, submit to the appropriate congressional committees an updated report with any additional entities of concern identified pursuant to subsection (b)(1). (2) Form.--The report required by this subsection shall be submitted in unclassified form, but may contain a classified annex. (e) Routine Assessment.--The Secretary of Commerce, in coordination with each agency that is a member of the Operating Committee for Export Policy, shall routinely assess for-- (1) model extraction attacks directed against owners of closed-source AI models that occur after the date of completion of the assessment required by this section; (2) fraudulent account network providers that facilitate model extraction attacks after the date of completion of the assessment required by this section; and (3) any material changes related to other matters specified in subsection (b). (f) Industry Coordination.--The Secretary of Commerce, in coordination with each agency that is a member of the Operating Committee for Export Policy, shall establish an information sharing mechanism that allows owners of closed-source AI models to voluntarily, quickly, and confidentially share information about model extraction attacks and fraudulent account network providers with the Department of Commerce. (g) AI Model Extraction Attackers List.-- (1) In general.--The Secretary of State, in coordination with each agency that is a member of the Operating Committee for Export Policy, shall-- (A) maintain a list, to be known as the ``AI Model Extraction Attackers List'', that displays information about specific individuals and entities of concern, that the assessment required by subsection (a) and routine assessment described in subsection (e) identify as having conducted or directed model extraction attacks in the past year; and (B) publish such list on a publicly available website of the Department of State for up to 5 years. (2) Protection of confidential information.--The Secretary of State may not, in publishing the list required by paragraph (1) on a publicly available website of the Department of State, disclose confidential information provided by owners of closed- source AI models without the express permission of said owner. (h) Public Guidance.--Not later than 210 days after the date of the enactment of this Act, the Secretary of Commerce, in coordination with each agency that is a member of the Operating Committee for Export Policy, shall publish a report comprising of best practices to detect, prevent, and respond to model extraction attacks. (1) Public access.--The report required by this subsection shall be publicly available. (2) Protection of confidential information.--In making the report required by this subsection publicly available, the Secretary of Commerce, in coordination with each agency that is a member of the Operating Committee for Export Policy, shall not disclose confidential information provided by owners of closed-source AI models without the express permission of said owner. SEC. 5. DETERRING MODEL EXTRACTION ATTACKS AND FRAUDULENT ACCOUNT NETWORK PROVIDERS. (a) Addition Consideration for Entity List.--Not later than 210 days after the date of the enactment of this Act, the Under Secretary of Commerce for Industry and Security, in coordination with each agency that is a member of the End-User Review Committee, shall make a determination by majority vote of the Committee on whether entities identified as having conducted model extraction attacks or having facilitated them via fraudulent account networks after the date of the completion of the assessment required under section 4 of this Act (identified pursuant to subsection (e) of such section), or any affiliate of such entity (to be determined by ownership of 50 percent or more in the aggregate, directly or indirectly), should be added to the Entity List maintained by the Bureau of Industry and Security of the Department of Commerce under Supplement No. 4 to part 744 of title 15, Code of Federal Regulations, or any successor regulations. (b) Sanctions Described.-- (1) In general.--The President, acting through the Secretary of State, may, pursuant to the International Emergency Economic Powers Act (50 U.S.C. 1701 et seq.), block and prohibit all transactions in all property and interests in property of entities of concern identified pursuant to subsections (b)(1) and (e) of section 4 if such property and interests in property are in the United States, come within the United States, or are or come within the possession or control of a United States person. (2) Exceptions.-- (A) Exception to comply with international obligations.--Sanctions under this subsection shall not apply with respect to the admission of an alien if admitting or paroling the alien into the United States is necessary to permit the United States to comply with the Agreement regarding the Headquarters of the United Nations, signed at Lake Success June 26, 1947, and entered into force November 21, 1947, between the United Nations and the United States, or other applicable international obligations. (B) Exception relating to the provision of humanitarian assistance.--Sanctions under this subsection may not be imposed with respect to transactions or the facilitation of transactions for-- (i) the sale of agricultural commodities, food, medicine, or medical devices; (ii) the provision of humanitarian assistance; (iii) financial transactions relating to humanitarian assistance; or (iv) transporting goods or services that are necessary to carry out operations relating to humanitarian assistance. (C) Exception for intelligence, law enforcement, and national security activities.--Sanctions under this subsection shall not apply to any authorized intelligence, law enforcement, or national security activities of the United States. (3) Penalties.--A person that violates, attempts to violate, conspires to violate, or causes a violation of this subsection or any regulation, license, or order issued to carry out that subsection shall be subject to the penalties set forth in subsections (b) and (c) of section 206 of the International Emergency Economic Powers Act (50 U.S.C. 1705) to the same extent as a person that commits an unlawful act described in subsection (a) of that section. <all>\n--- KONIEC DOKUMENTU ---\n\nPAMIĘTAJ: Twoja odpowiedź MUSI być wyłącznie poprawnym obiektem JSON. Nie dodawaj żadnych dodatkowych znaków, komentarzy ani tekstu przed znacznikiem '{' ani po znaczniku '}'. Cała odpowiedź musi być parsowalna jako JSON.\nNa podstawie POWYŻSZEGO dokumentu, wypełnij poniższą strukturę JSON:\nOto struktura JSON, której oczekuję (wypełnij ją treścią):\n{\n  \"pl_ai_title\": \"Nowy, krótki tytuł dla aktu prawnego po polsku, oddający sedno wprowadzanych zmian (np. maksymalnie 10-12 słów).\",\n  \"pl_summary\": \"2-3 zdania zwięzłego podsumowania treści aktu prawnego po polsku, napisane z perspektywy wpływu na życie codzienne obywateli.\",\n  \"pl_key_points\": [\n    \"Pierwszy krótki punkt po polsku dotyczący najważniejszych wprowadzanych rozwiązań lub zmian.\",\n    \"Drugi krótki punkt po polsku...\"\n  ],\n  \"eng_ai_title\": \"A new, short title for the legal act in English, capturing the essence of the changes (e.g., max 10-12 words).\",\n  \"eng_summary\": \"2-3 sentences summarizing the legal act in English, from the perspective of its impact on citizens' daily lives.\",\n  \"eng_key_points\": [\n    \"First short bullet point in English regarding the most important solutions or changes being introduced.\",\n    \"Second short bullet point in English...\"\n  ],\n  \"de_ai_title\": \"Ein neuer, kurzer Titel für das Rechtsdokument auf Deutsch, der den Kern der Änderungen erfasst (z.B. max. 10-12 Wörter).\",\n  \"de_summary\": \"2-3 Sätze Zusammenfassung des Rechtsdokuments auf Deutsch, aus der Perspektive seiner Auswirkungen auf das tägliche Leben der Bürger.\",\n  \"de_key_points\": [\n    \"Erster kurzer Stichpunkt auf Deutsch zu den wichtigsten eingeführten Lösungen oder Änderungen.\",\n    \"Zweiter kurzer Stichpunkt auf Deutsch...\"\n  ],\n  \"fr_ai_title\": \"Un nouveau titre court pour l'acte juridique en français, saisissant l'essence des changements (par exemple, 10-12 mots maximum).\",\n  \"fr_summary\": \"Résumé de 2-3 phrases de l'acte juridique en français, du point de vue de son impact sur la vie quotidienne des citoyens.\",\n  \"fr_key_points\": [\n    \"Premier court point en français concernant les solutions ou changements les plus importants introduits.\",\n    \"Deuxième court point en français...\"\n  ],\n  \"es_ai_title\": \"Un nuevo título breve para el acto jurídico en español, que recoja la esencia de los cambios (por ejemplo, máximo 10-12 palabras).\",\n  \"es_summary\": \"Resumen de 2-3 frases del acto jurídico en español, desde la perspectiva de su impacto en la vida cotidiana de los ciudadanos.\",\n  \"es_key_points\": [\n    \"Primer punto breve en español sobre las soluciones o cambios más importantes que se introducen.\",\n    \"Segundo punto breve en español...\"\n  ],\n  \"it_ai_title\": \"Un nuovo titolo breve per l'atto giuridico in italiano, che colga l'essenza delle modifiche (ad es. massimo 10-12 parole).\",\n  \"it_summary\": \"Riepilogo di 2-3 frasi dell'atto giuridico in italiano, dal punto di vista del suo impatto sulla vita quotidiana dei cittadini.\",\n  \"it_key_points\": [\n    \"Primo breve punto in italiano riguardante le soluzioni o le modifiche più importanti introdotte.\",\n    \"Secondo breve punto in italiano...\"\n  ],\n  \"nl_ai_title\": \"Een nieuwe, korte titel voor de rechtshandeling in het Nederlands, die de essentie van de wijzigingen weergeeft (bijv. max. 10-12 woorden).\",\n  \"nl_summary\": \"Samenvatting van 2-3 zinnen van de rechtshandeling in het Nederlands, vanuit het perspectief van de impact op het dagelijks leven van burgers.\",\n  \"nl_key_points\": [\n    \"Eerste korte punt in het Nederlands betreffende de belangrijkste geïntroduceerde oplossingen of wijzigingen.\",\n    \"Tweede korte punt in het Nederlands...\"\n  ],\n  \"pt_ai_title\": \"Um novo título curto para o ato jurídico em português, capturando a essência das mudanças (por exemplo, máx. 10-12 palavras).\",\n  \"pt_summary\": \"Resumo de 2-3 frases do ato jurídico em português, na perspetiva do seu impacto na vida quotidiana dos cidadãos.\",\n  \"pt_key_points\": [\n    \"Primeiro ponto curto em português sobre as soluções ou alterações mais importantes introduzidas.\",\n    \"Segundo ponto curto em português...\"\n  ],\n  \"category\": [\"Categorize the document into one category by default, based on the field it primarily concerns. Choose up to 3 if the document also touches upon SIGNIFICANT issues from other categories. You MUST select categories ONLY from the following list: Health, Education, Family, Taxes, Labor, Security, Environment, Courts and Law, Transport, Benefits, Real Estate, Media and Culture, Local Government, Migration, Agriculture, Public Investments, Informatization, Economy. If the document does not definitively fit any of these, you MUST use \"Other\". If you use \"Other\", it should be the ONLY category selected. Do NOT invent new categories. The response must be an array of strings, e.g., [\"Taxes\", \"Family\"].\"]\n}\n\n",
      "ai_response_raw": "{\n  \"pl_ai_title\": \"Ustawa o ochronie amerykańskich modeli sztucznej inteligencji przed kradzieżą z 2026 roku\",\n  \"pl_summary\": \"Ustawa ma na celu ochronę zaawansowanych technologii sztucznej inteligencji przed kradzieżą przez obce państwa, co zwiększa bezpieczeństwo narodowe i chroni innowacje. Obywatele mogą spodziewać się większej ochrony technologii napędzających gospodarkę oraz surowych kar dla podmiotów próbujących nielegalnie kopiować amerykańskie rozwiązania.\",\n  \"pl_key_points\": [\n    \"Zakaz nielegalnego kopiowania kluczowych cech technicznych modeli AI przez zagraniczne podmioty.\",\n    \"Wprowadzenie sankcji finansowych i blokady majątków dla osób i firm kradnących technologię AI.\",\n    \"Utworzenie publicznej listy podmiotów i krajów uznanych za sprawców ataków na systemy AI.\",\n    \"Uruchomienie systemu dobrowolnej współpracy firm technologicznych z rządem w celu wykrywania zagrożeń.\",\n    \"Opracowanie najlepszych praktyk obronnych dla właścicieli technologii w celu zapobiegania atakom.\"\n  ],\n  \"eng_ai_title\": \"Deterring American AI Model Theft Act of 2026\",\n  \"eng_summary\": \"This act protects advanced US artificial intelligence from being stolen by foreign adversaries to safeguard national security and economic interests. It establishes measures to identify and punish entities that attempt to illegally copy proprietary AI technology.\",\n  \"eng_key_points\": [\n    \"Bans unauthorized extraction of key technical features from closed-source AI models.\",\n    \"Imposes economic sanctions and property blocks on foreign entities involved in AI theft.\",\n    \"Creates a public list of individuals and entities identified as AI model attackers.\",\n    \"Establishes a voluntary information-sharing mechanism between tech companies and the government.\",\n    \"Requires the development of best practices to detect and prevent AI extraction attacks.\"\n  ],\n  \"de_ai_title\": \"Gesetz zur Verhinderung des Diebstahls amerikanischer KI-Modelle von 2026\",\n  \"de_summary\": \"Dieses Gesetz schützt fortschrittliche US-KI-Modelle vor Diebstahl durch ausländische Gegner, um die nationale Sicherheit und wirtschaftliche Interessen zu wahren. Es führt Maßnahmen zur Identifizierung und Bestrafung von Organisationen ein, die versuchen, geschützte KI-Technologien illegal zu kopieren.\",\n  \"de_key_points\": [\n    \"Verbot der unbefugten Extraktion technischer Merkmale aus geschlossenen KI-Modellen.\",\n    \"Wirtschaftssanktionen und Vermögenssperren für ausländische Akteure bei Technologiediebstahl.\",\n    \"Veröffentlichung einer Liste von Personen und Organisationen, die KI-Angriffe durchführen.\",\n    \"Einrichtung eines Mechanismus zum freiwilligen Informationsaustausch zwischen Unternehmen und Behörden.\",\n    \"Entwicklung von Leitfäden zur Erkennung und Abwehr von Angriffen auf KI-Systeme.\"\n  ],\n  \"fr_ai_title\": \"Loi de 2026 sur la protection des modèles d'IA américains contre le vol\",\n  \"fr_summary\": \"Cette loi vise à empêcher les adversaires étrangers de voler les caractéristiques techniques des modèles d'intelligence artificielle américains pour protéger la sécurité nationale. Elle établit des mesures pour identifier et sanctionner les entités tentant de copier illégalement des technologies propriétaires.\",\n  \"fr_key_points\": [\n    \"Interdiction de l'extraction non autorisée de caractéristiques clés des modèles d'IA.\",\n    \"Sanctions économiques et gel des avoirs pour les entités étrangères impliquées dans le vol d'IA.\",\n    \"Création d'une liste publique des individus et entités identifiés comme attaquants de modèles d'IA.\",\n    \"Mise en place d'un mécanisme de partage d'informations entre le gouvernement et le secteur privé.\",\n    \"Publication de meilleures pratiques pour détecter et prévenir les attaques par extraction.\"\n  ],\n  \"es_ai_title\": \"Ley de 2026 para prevenir el robo de modelos de IA estadounidenses\",\n  \"es_summary\": \"Esta ley protege la inteligencia artificial avanzada de EE. UU. contra el robo por parte de adversarios extranjeros para garantizar la seguridad nacional y los intereses económicos. Establece medidas para identificar y sancionar a quienes intenten copiar ilegalmente tecnología patentada.\",\n  \"es_key_points\": [\n    \"Prohibición de la extracción no autorizada de funciones técnicas clave de modelos de IA.\",\n    \"Sanciones económicas y bloqueo de propiedades para entidades extranjeras que roben tecnología.\",\n    \"Creación de una lista pública de personas y entidades identificadas como atacantes de IA.\",\n    \"Mecanismo de intercambio voluntario de información entre empresas tecnológicas y el gobierno.\",\n    \"Desarrollo de guías de mejores prácticas para detectar y responder a ataques cibernéticos.\"\n  ],\n  \"it_ai_title\": \"Legge del 2026 contro il furto dei modelli di IA americani\",\n  \"it_summary\": \"Questa legge protegge l'intelligenza artificiale avanzata degli Stati Uniti dal furto da parte di avversari stranieri per salvaguardare la sicurezza nazionale. Introduce sanzioni per le entità che tentano di copiare illegalmente tecnologie proprietarie fondamentali.\",\n  \"it_key_points\": [\n    \"Divieto di estrazione non autorizzata di caratteristiche tecniche dai modelli di IA chiusi.\",\n    \"Sanzioni economiche e blocco dei beni per entità straniere coinvolte nel furto di IA.\",\n    \"Pubblicazione di un elenco di soggetti e organizzazioni che effettuano attacchi ai modelli di IA.\",\n    \"Collaborazione volontaria tra aziende e governo per la condivisione di informazioni sulle minacce.\",\n    \"Definizione di linee guida per rilevare e prevenire tentativi di furto tecnologico.\"\n  ],\n  \"nl_ai_title\": \"Wet tegen diefstal van Amerikaanse AI-modellen van 2026\",\n  \"nl_summary\": \"Deze wet beschermt geavanceerde Amerikaanse AI-technologie tegen diefstal door buitenlandse mogendheden om de nationale veiligheid te waarborgen. Het stelt maatregelen vast om entiteiten die illegaal technologie kopiëren te identificeren en te straffen.\",\n  \"nl_key_points\": [\n    \"Verbod op het ongeoorloofd extraheren van technische kenmerken uit AI-modellen.\",\n    \"Economische sancties en bevriezing van tegoeden voor buitenlandse partijen bij AI-diefstal.\",\n    \"Openbare lijst van personen en organisaties die AI-aanvallen uitvoeren.\",\n    \"Vrijwillige informatie-uitwisseling tussen techbedrijven en de overheid over dreigingen.\",\n    \"Ontwikkeling van richtlijnen voor het detecteren en voorkomen van technologische diefstal.\"\n  ],\n  \"pt_ai_title\": \"Lei de 2026 para prevenir o roubo de modelos de IA americanos\",\n  \"pt_summary\": \"Esta lei protege a inteligência artificial avançada dos EUA contra o roubo por adversários estrangeiros para garantir a segurança nacional. Estabelece mecanismos para identificar e punir entidades que tentem copiar ilegalmente tecnologias proprietárias.\",\n  \"pt_key_points\": [\n    \"Proibição da extração não autorizada de características técnicas de modelos de IA.\",\n    \"Sanções económicas e bloqueio de bens para entidades estrangeiras envolvidas no roubo de IA.\",\n    \"Criação de uma lista pública de indivíduos e entidades que atacam sistemas de IA.\",\n    \"Mecanismo de partilha voluntária de informações entre o governo e o setor privado.\",\n    \"Desenvolvimento de boas práticas para detetar e prevenir ataques de extração de modelos.\"\n  ],\n  \"category\": [\"Security\", \"Economy\", \"Informatization\"]\n}"
    }
  ]
}