FuzzBench: 2024-08-28-empty-seeds-1 report

experiment summary

We show two different aggregate (cross-benchmark) rankings of fuzzers. The first is based on the average of per-benchmarks scores, where the score represents the percentage of the highest reached median code-coverage on a given benchmark (higher value is better). The second ranking shows the average rank of fuzzers, after we rank them on each benchmark according to their median reached code-covereges (lower value is better).

By avg. score

	average normalized score
fuzzer
eclipser	85.76
mopt	84.06
aflsmart	83.55
aflfast	82.72
fairfuzz	80.47
libafl	76.04
centipede	71.96
afl	4.75
libfuzzer	4.43

By avg. rank

	average rank
fuzzer
aflsmart	3.05
eclipser	3.19
libafl	3.19
mopt	3.71
fairfuzz	4.67
aflfast	4.81
centipede	4.81
afl	7.33
libfuzzer	7.52

Critical difference diagram

The diagram visualizes the average rank of fuzzers (second ranking above) while showing the significance of the differences as well. What is considered a "critical difference" (CD) is based on the Friedman/Nemenyi post-hoc test. See more in the documentation.

Note: If a fuzzer does not support all benchmarks, its ranking as shown in this diagram can be lower than it should be. So please check the list of supported benchmarks for the fuzzer(s) of your interest. The list could be specified in the fuzzer's README.md like this.

Median relative code-coverages on each benchmark

Note: The relative coverage summary table shows the median relative performance of each fuzzer to the experiment maximum. Thus the highest relative performance may not be 100%.
trial_relative_coverage = trial_coverage / experiment_max_coverage

	libafl	afl	libfuzzer	eclipser	mopt	aflsmart	centipede	aflfast	fairfuzz
FuzzerMedian	98.00	95.00	89.00	94.00	94.00	94.00	91.50	93.00	86.00
FuzzerMean	96.50	95.00	89.00	88.26	80.52	80.10	79.50	79.48	77.05
bloaty_fuzz_target	nan	95.00	89.00	94.00	96.00	94.00	nan	93.00	80.00
curl_curl_fuzzer_http	99.00	nan	nan	94.00	94.00	94.00	nan	93.00	85.00
freetype2_ftfuzzer	91.00	nan	nan	74.00	67.00	67.00	57.00	64.00	63.00
harfbuzz_hb-shape-fuzzer	nan	nan	nan	98.00	99.00	98.00	nan	97.00	86.00
jsoncpp_jsoncpp_fuzzer	98.00	nan	nan	98.00	98.00	98.00	98.00	98.00	98.00
lcms_cms_transform_fuzzer	nan	nan	nan	80.00	54.00	43.00	38.00	30.00	59.00
libjpeg-turbo_libjpeg_turbo_fuzzer	99.00	nan	nan	nan	82.00	82.00	97.00	98.00	99.00
libpcap_fuzz_both	nan	nan	nan	71.00	0.00	0.00	81.00	1.00	0.00
libpng_libpng_read_fuzzer	95.00	nan	nan	95.00	94.00	95.00	96.00	93.00	95.00
libxml2_xml	99.00	nan	nan	97.00	97.00	97.00	93.00	97.00	89.00
libxslt_xpath	97.00	nan	nan	95.00	94.00	96.00	94.00	94.00	96.00
mbedtls_fuzz_dtlsclient	91.00	nan	nan	70.00	70.00	70.00	69.00	68.00	73.00
openssl_x509	99.00	nan	nan	99.00	99.00	99.00	99.00	99.00	99.00
openthread_ot-ip6-send-fuzzer	88.00	nan	nan	74.00	71.00	71.00	70.00	71.00	68.00
proj4_proj_crs_to_crs_fuzzer	nan	nan	nan	64.00	10.00	10.00	10.00	9.00	10.00
re2_fuzzer	99.00	nan	nan	99.00	99.00	99.00	96.00	99.00	99.00
sqlite3_ossfuzz	99.00	nan	nan	90.00	90.00	90.00	61.00	90.00	57.00
systemd_fuzz-link-parser	99.00	nan	nan	91.00	91.00	92.00	98.00	92.00	87.00
vorbis_decode_fuzzer	98.00	nan	nan	98.00	98.00	98.00	90.00	98.00	97.00
woff2_convert_woff2ttf_fuzzer	98.00	nan	nan	nan	92.00	93.00	89.00	90.00	82.00
zlib_zlib_uncompress_fuzzer	95.00	nan	nan	96.00	96.00	96.00	95.00	95.00	96.00

Fuzzers are sorted by "FuzzerMean" (average median relative coverage), highest on the left.
Green background = highest relative median coverage.
Blue gradient background = greater than 95% relative median coverage.

bloaty_fuzz_target summary

Ranking by median reached code coverage

Mean code coverage growth over time

* The error bands show the 95% confidence interval around the mean code coverage.

The following fuzzers do not have enough samples: eclipser, libfuzzer, afl.

Sample statistics and statistical significance (code coverage)

Code coverage sample statistics

		count	mean	std	min	25%	median	75%	max
fuzzer	time
mopt	53100	20.0	6100.400000	111.005168	5899.0	6016.00	6127.0	6204.75	6258.0
afl	53100	2.0	6110.500000	136.471609	6014.0	6062.25	6110.5	6158.75	6207.0
eclipser	53100	11.0	5998.454545	78.741811	5884.0	5924.50	6034.0	6046.50	6113.0
aflsmart	53100	20.0	6045.950000	123.503878	5736.0	6002.00	6029.0	6087.00	6274.0
aflfast	53100	20.0	5995.200000	125.738911	5788.0	5913.50	5996.5	6045.25	6304.0
libfuzzer	53100	6.0	5723.333333	152.381976	5551.0	5608.75	5697.5	5837.25	5931.0
fairfuzz	53100	16.0	5170.000000	56.041651	5109.0	5123.75	5154.5	5208.00	5294.0

Vargha-Delaney A12 measure

The table summarizes the A12 values from the pairwise Vargha-Delaney A measure of effect size. Green cells indicate the probability the fuzzer in the row will outperform the fuzzer in the column.

Mann-Whitney U test

The table summarizes the p values of pairwise Mann-Whitney U tests. Green cells indicate that the reached coverage distribution of a given fuzzer pair is significantly different.

Unique code coverage plots

Ranking by unique code branches covered
Each bar shows the total number of code branches found by a given fuzzer. The colored area shows the number of unique code branches (i.e., branches that were not covered by any other fuzzers).

Pairwise unique code coverage
Each cell represents the number of code branches covered by the fuzzer of the column but not by the fuzzer of the row

Code coverage reports for each fuzzer on this benchmark

afl afl_empty_seeds aflfast aflplusplus aflplusplus_empty_seeds aflsmart centipede eclipser fairfuzz honggfuzz honggfuzz_empty_seeds libafl libfuzzer libfuzzer_empty_seeds mopt