FuzzBench: 2024-05-18-formatfuzz 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
formatfuzz	97.72
aflplusplus	97.58
libafl	97.17
honggfuzz	94.41
libfuzzer	93.58
afl	82.48
mopt	81.07
aflsmart	80.06
aflfast	79.72
fairfuzz	79.01
eclipser	75.48
centipede	69.03

By avg. rank

	average rank
fuzzer
formatfuzz	2.18
aflplusplus	2.73
libafl	4.55
libfuzzer	4.64
honggfuzz	6.45
aflsmart	6.73
afl	7.27
mopt	7.27
eclipser	7.36
fairfuzz	8.82
aflfast	9.09
centipede	9.18

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

	formatfuzz	aflplusplus	libafl	honggfuzz	libfuzzer	eclipser	centipede	afl	mopt	aflsmart	aflfast	fairfuzz
FuzzerMedian	97.00	97.00	95.00	95.00	94.00	95.00	89.00	93.00	94.00	94.00	93.00	84.00
FuzzerMean	94.82	94.73	94.27	91.45	90.91	89.56	81.67	80.36	79.09	78.09	77.82	77.18
bloaty_fuzz_target	98.00	98.00	98.00	92.00	91.00	94.00	nan	93.00	95.00	94.00	93.00	80.00
freetype2_ftfuzzer	93.00	91.00	90.00	91.00	77.00	74.00	58.00	66.00	66.00	67.00	65.00	63.00
harfbuzz_hb-shape-fuzzer	98.00	98.00	99.00	96.00	94.00	97.00	nan	96.00	97.00	96.00	96.00	84.00
lcms_cms_transform_fuzzer	92.00	92.00	94.00	73.00	86.00	75.00	37.00	67.00	51.00	40.00	29.00	55.00
libjpeg-turbo_libjpeg_turbo_fuzzer	82.00	82.00	82.00	82.00	82.00	nan	82.00	82.00	82.00	82.00	99.00	99.00
libpcap_fuzz_both	92.00	94.00	91.00	89.00	82.00	79.00	91.00	1.00	1.00	1.00	1.00	1.00
libpng_libpng_read_fuzzer	95.00	95.00	95.00	95.00	96.00	95.00	96.00	94.00	94.00	94.00	93.00	94.00
openssl_x509	99.00	99.00	99.00	98.00	99.00	99.00	99.00	99.00	99.00	99.00	98.00	99.00
vorbis_decode_fuzzer	99.00	98.00	97.00	96.00	98.00	97.00	88.00	97.00	97.00	97.00	97.00	96.00
woff2_convert_woff2ttf_fuzzer	97.00	98.00	98.00	97.00	96.00	nan	89.00	93.00	92.00	93.00	91.00	82.00
zlib_zlib_uncompress_fuzzer	98.00	97.00	94.00	97.00	99.00	96.00	95.00	96.00	96.00	96.00	94.00	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.

Sample statistics and statistical significance (code coverage)

Code coverage sample statistics

		count	mean	std	min	25%	median	75%	max
fuzzer	time
libafl	82800	20.0	6343.000000	41.929766	6252.0	6324.25	6352.0	6367.00	6402.0
formatfuzz	82800	20.0	6289.150000	122.280211	6026.0	6198.75	6342.5	6383.75	6453.0
aflplusplus	82800	20.0	6328.300000	69.291224	6149.0	6327.50	6340.0	6368.00	6429.0
mopt	82800	20.0	6189.050000	93.155487	6019.0	6121.00	6188.0	6260.50	6323.0
aflsmart	82800	20.0	6146.000000	146.262561	5784.0	6070.75	6104.0	6271.00	6381.0
eclipser	82800	11.0	6053.181818	68.930136	5914.0	6022.50	6078.0	6095.50	6135.0
afl	82800	20.0	6040.550000	112.988809	5838.0	5956.50	6062.5	6098.75	6233.0
aflfast	82800	17.0	6028.411765	77.961576	5893.0	5960.00	6035.0	6065.00	6185.0
honggfuzz	82800	20.0	6044.800000	190.055560	5739.0	5920.75	5971.0	6222.50	6334.0
libfuzzer	82800	20.0	5899.050000	118.185614	5708.0	5797.75	5905.0	5980.25	6141.0
fairfuzz	82800	16.0	5189.937500	67.159977	5111.0	5135.25	5170.0	5226.00	5323.0

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 aflfast aflplusplus aflsmart centipede eclipser fairfuzz formatfuzz honggfuzz libafl libfuzzer mopt