A New Approach to Correlated Multi Armed Bandits

Juneja, Ishank; Gaharwar, Devanshu Singh; Varshney, Dhruv; Moharir, Sharayu

doi:10.1109/comsnets48256.2020.9027344

Cited by 2 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternatively, in a PUT that has a limit on the length of inputs to be accepted, mutations such as inserting a constant string or copying a partial byte sequence from another seed are not promising arms. While the distributions of rewards are assumed to be independent in standard stochastic bandit problems, there are studies on such problem settings where the arms are correlated, aimed at reducing regret further compared to the standard settings [30,33,55]. Even assuming independence, bandit algorithms can greatly improve the efficiency of the fuzzer.…”

Section: Correlation Of Armsmentioning

confidence: 99%

SLOPT: Bandit Optimization Framework for Mutation-Based Fuzzing

Koike¹,

Katsura²,

Yakura³

et al. 2022

Proceedings of the 38th Annual Computer Security Applications Conference

View full text Add to dashboard Cite

Mutation-based fuzzing has become one of the most common vulnerability discovery solutions over the last decade. Fuzzing can be optimized when targeting specific programs, and given that, some studies have employed online optimization methods to do it automatically, i.e., tuning fuzzers for any given program in a program-agnostic manner. However, previous studies have neither fully explored mutation schemes suitable for online optimization methods, nor online optimization methods suitable for mutation schemes. In this study, we propose an optimization framework called SLOPT that encompasses both a bandit-friendly mutation scheme and mutation-scheme-friendly bandit algorithms. The advantage of SLOPT is that it can generally be incorporated into existing fuzzers, such as AFL and Honggfuzz. As a proof of concept, we implemented SLOPT-AFL++ by integrating SLOPT into AFL++ and showed that the program-agnostic optimization delivered by SLOPT enabled SLOPT-AFL++ to achieve higher code coverage than AFL++ in all of ten real-world FuzzBench programs. Moreover, we ran SLOPT-AFL++ against several real-world programs from OSS-Fuzz and successfully identified three previously unknown vulnerabilities, even though these programs have been fuzzed by AFL++ for a considerable number of CPU days on OSS-Fuzz. CCS CONCEPTS• Security and privacy → Software security engineering; • Theory of computation → Sequential decision making.

show abstract

Section: Correlation Of Armsmentioning

confidence: 99%