Matches in SemOpenAlex for { <https://semopenalex.org/work/W2898895607> ?p ?o ?g. }
- W2898895607 abstract "Fuzzing has become the de facto standard technique for finding software vulnerabilities. However, even state-of-the-art fuzzers are not very efficient at finding hard-to-trigger software bugs. Most popular fuzzers use evolutionary guidance to generate inputs that can trigger different bugs. Such evolutionary algorithms, while fast and simple to implement, often get stuck in fruitless sequences of random mutations. Gradient-guided optimization presents a promising alternative to evolutionary guidance. Gradient-guided techniques have been shown to significantly outperform evolutionary algorithms at solving high-dimensional structured optimization problems in domains like machine learning by efficiently utilizing gradients or higher-order derivatives of the underlying function. However, gradient-guided approaches are not directly applicable to fuzzing as real-world program behaviors contain many discontinuities, plateaus, and ridges where the gradient-based methods often get stuck. We observe that this problem can be addressed by creating a smooth surrogate function approximating the discrete branching behavior of target program. In this paper, we propose a novel program smoothing technique using surrogate neural network models that can incrementally learn smooth approximations of a complex, real-world program's branching behaviors. We further demonstrate that such neural network models can be used together with gradient-guided input generation schemes to significantly improve the fuzzing efficiency. Our extensive evaluations demonstrate that NEUZZ significantly outperforms 10 state-of-the-art graybox fuzzers on 10 real-world programs both at finding new bugs and achieving higher edge coverage. NEUZZ found 31 unknown bugs that other fuzzers failed to find in 10 real world programs and achieved 3X more edge coverage than all of the tested graybox fuzzers for 24 hours running." @default.
- W2898895607 created "2018-11-09" @default.
- W2898895607 creator A5007048525 @default.
- W2898895607 creator A5016425387 @default.
- W2898895607 creator A5048358055 @default.
- W2898895607 creator A5056288677 @default.
- W2898895607 creator A5064541855 @default.
- W2898895607 creator A5084112173 @default.
- W2898895607 date "2018-07-15" @default.
- W2898895607 modified "2023-09-23" @default.
- W2898895607 title "NEUZZ: Efficient Fuzzing with Neural Program Smoothing" @default.
- W2898895607 cites W1409984952 @default.
- W2898895607 cites W1506510492 @default.
- W2898895607 cites W1507845365 @default.
- W2898895607 cites W1518078339 @default.
- W2898895607 cites W1525859397 @default.
- W2898895607 cites W1546956568 @default.
- W2898895607 cites W157156687 @default.
- W2898895607 cites W1682403713 @default.
- W2898895607 cites W1710734607 @default.
- W2898895607 cites W1720848645 @default.
- W2898895607 cites W1777846110 @default.
- W2898895607 cites W1825675169 @default.
- W2898895607 cites W1915485278 @default.
- W2898895607 cites W1966878414 @default.
- W2898895607 cites W1971735090 @default.
- W2898895607 cites W1976878954 @default.
- W2898895607 cites W1988115241 @default.
- W2898895607 cites W1996340400 @default.
- W2898895607 cites W2000359198 @default.
- W2898895607 cites W2002934700 @default.
- W2898895607 cites W2009489720 @default.
- W2898895607 cites W2019411264 @default.
- W2898895607 cites W2027718224 @default.
- W2898895607 cites W2042033151 @default.
- W2898895607 cites W2051669046 @default.
- W2898895607 cites W2092826572 @default.
- W2898895607 cites W2096449544 @default.
- W2898895607 cites W2097444001 @default.
- W2898895607 cites W2101512909 @default.
- W2898895607 cites W2101533953 @default.
- W2898895607 cites W2107147876 @default.
- W2898895607 cites W2109596254 @default.
- W2898895607 cites W2112796928 @default.
- W2898895607 cites W2116522068 @default.
- W2898895607 cites W2128128820 @default.
- W2898895607 cites W2130325614 @default.
- W2898895607 cites W2131275552 @default.
- W2898895607 cites W2143386621 @default.
- W2898895607 cites W2149801502 @default.
- W2898895607 cites W2162737890 @default.
- W2898895607 cites W2163605009 @default.
- W2898895607 cites W2163913714 @default.
- W2898895607 cites W2180612164 @default.
- W2898895607 cites W2295283246 @default.
- W2898895607 cites W2499791918 @default.
- W2898895607 cites W2515236103 @default.
- W2898895607 cites W2535617737 @default.
- W2898895607 cites W2557283755 @default.
- W2898895607 cites W2560647685 @default.
- W2898895607 cites W2574017551 @default.
- W2898895607 cites W2583649498 @default.
- W2898895607 cites W2583761661 @default.
- W2898895607 cites W2594940144 @default.
- W2898895607 cites W2613534458 @default.
- W2898895607 cites W2672575173 @default.
- W2898895607 cites W2701225458 @default.
- W2898895607 cites W2741068848 @default.
- W2898895607 cites W2743151379 @default.
- W2898895607 cites W2752340395 @default.
- W2898895607 cites W2767634461 @default.
- W2898895607 cites W2769748476 @default.
- W2898895607 cites W2783428950 @default.
- W2898895607 cites W2795192879 @default.
- W2898895607 cites W2810533955 @default.
- W2898895607 cites W2949800357 @default.
- W2898895607 cites W2950527759 @default.
- W2898895607 cites W2962851944 @default.
- W2898895607 cites W2963207607 @default.
- W2898895607 cites W2963929497 @default.
- W2898895607 cites W2963937837 @default.
- W2898895607 cites W2964097210 @default.
- W2898895607 cites W2996489182 @default.
- W2898895607 cites W3029645440 @default.
- W2898895607 cites W3102438316 @default.
- W2898895607 cites W72823879 @default.
- W2898895607 cites W2054374813 @default.
- W2898895607 doi "https://doi.org/10.48550/arxiv.1807.05620" @default.
- W2898895607 hasPublicationYear "2018" @default.
- W2898895607 type Work @default.
- W2898895607 sameAs 2898895607 @default.
- W2898895607 citedByCount "5" @default.
- W2898895607 countsByYear W28988956072019 @default.
- W2898895607 countsByYear W28988956072020 @default.
- W2898895607 crossrefType "posted-content" @default.
- W2898895607 hasAuthorship W2898895607A5007048525 @default.
- W2898895607 hasAuthorship W2898895607A5016425387 @default.
- W2898895607 hasAuthorship W2898895607A5048358055 @default.
- W2898895607 hasAuthorship W2898895607A5056288677 @default.
- W2898895607 hasAuthorship W2898895607A5064541855 @default.