Yaohui Chen

Manish Bhatt, Sahana Chennabasappa, Yue Li et al.

Large language models (LLMs) introduce new security risks, but there are few comprehensive evaluation suites to measure and reduce these risks. We present BenchmarkName, a novel benchmark to quantify LLM security risks and capabilities. We introduce two new areas for testing: prompt injection and code interpreter abuse. We evaluated multiple state-of-the-art (SOTA) LLMs, including GPT-4, Mistral, Meta Llama 3 70B-Instruct, and Code Llama. Our results show that conditioning away risk of attack remains an unsolved problem; for example, all tested models showed between 26% and 41% successful prompt injection tests. We further introduce the safety-utility tradeoff: conditioning an LLM to reject unsafe prompts can cause the LLM to falsely reject answering benign prompts, which lowers utility. We propose quantifying this tradeoff using False Refusal Rate (FRR). As an illustration, we introduce a novel test set to quantify FRR for cyberattack helpfulness risk. We find many LLMs able to successfully comply with "borderline" benign requests while still rejecting most unsafe requests. Finally, we quantify the utility of LLMs for automating a core cybersecurity task, that of exploiting software vulnerabilities. This is important because the offensive capabilities of LLMs are of intense interest; we quantify this by creating novel test sets for four representative problems. We find that models with coding capabilities perform better than those without, but that further work is needed for LLMs to become proficient at exploit generation. Our code is open source and can be used to evaluate other LLMs.

Yaohui Chen, Mansour Ahmadi, Reza Mirzazade farkhani et al.

Seed scheduling is a prominent factor in determining the yields of hybrid fuzzing. Existing hybrid fuzzers schedule seeds based on fixed heuristics that aim to predict input utilities. However, such heuristics are not generalizable as there exists no one-size-fits-all rule applicable to different programs. They may work well on the programs from which they were derived, but not others. To overcome this problem, we design a Machine learning-Enhanced hybrid fUZZing system (MEUZZ), which employs supervised machine learning for adaptive and generalizable seed scheduling. MEUZZ determines which new seeds are expected to produce better fuzzing yields based on the knowledge learned from past seed scheduling decisions made on the same or similar programs. MEUZZ's learning is based on a series of features extracted via code reachability and dynamic analysis, which incurs negligible runtime overhead (in microseconds). Moreover, MEUZZ automatically infers the data labels by evaluating the fuzzing performance of each selected seed. As a result, MEUZZ is generally applicable to, and performs well on, various kinds of programs. Our evaluation shows MEUZZ significantly outperforms the state-of-the-art grey-box and hybrid fuzzers, achieving 27.1% more code coverage than QSYM. The learned models are reusable and transferable, which boosts fuzzing performance by 7.1% on average and improves 68% of the 56 cross-program fuzzing campaigns. MEUZZ discovered 47 deeply hidden and previously unknown bugs--with 21 confirmed and fixed by the developers--when fuzzing 8 well-tested programs with the same configurations as used in previous work.

Yaohui Chen, Peng Li, Jun Xu et al.

Hybrid testing combines fuzz testing and concolic execution. It leverages fuzz testing to test easy-to-reach code regions and uses concolic execution to explore code blocks guarded by complex branch conditions. However, its code coverage-centric design is inefficient in vulnerability detection. First, it blindly selects seeds for concolic execution and aims to explore new code continuously. However, as statistics show, a large portion of the explored code is often bug-free. Therefore, giving equal attention to every part of the code during hybrid testing is a non-optimal strategy. It slows down the detection of real vulnerabilities by over 43%. Second, classic hybrid testing quickly moves on after reaching a chunk of code, rather than examining the hidden defects inside. It may frequently miss subtle vulnerabilities despite that it has already explored the vulnerable code paths. We propose SAVIOR, a new hybrid testing framework pioneering a bug-driven principle. Unlike the existing hybrid testing tools, SAVIOR prioritizes the concolic execution of the seeds that are likely to uncover more vulnerabilities. Moreover, SAVIOR verifies all vulnerable program locations along the executing program path. By modeling faulty situations using SMT constraints, SAVIOR reasons the feasibility of vulnerabilities and generates concrete test cases as proofs. Our evaluation shows that the bug-driven approach outperforms mainstream automated testing techniques, including state-of-the-art hybrid testing systems driven by code coverage. On average, SAVIOR detects vulnerabilities 43.4% faster than DRILLER and 44.3% faster than QSYM, leading to the discovery of 88 and 76 more uniquebugs,respectively.Accordingtotheevaluationon11 well fuzzed benchmark programs, within the first 24 hours, SAVIOR triggers 481 UBSAN violations, among which 243 are real bugs.

Yaohui Chen, Dongliang Mu, Jun Xu et al.

Despite its effectiveness in uncovering software defects, American Fuzzy Lop (AFL), one of the best grey-box fuzzers, is inefficient when fuzz-testing source-unavailable programs. AFL's binary-only fuzzing mode, QEMU-AFL, is typically 2-5X slower than its source-available fuzzing mode. The slowdown is largely caused by the heavy dynamic instrumentation. Recent fuzzing techniques use Intel Processor Tracing (PT), a light-weight tracing feature supported by recent Intel CPUs, to remove the need of dynamic instrumentation. However, we found that these PT-based fuzzing techniques are even slower than QEMU-AFL when fuzzing real-world programs, making them less effective than QEMU-AFL. This poor performance is caused by the slow extraction of code coverage information from highly compressed PT traces. In this work, we present the design and implementation of PTrix, which fully unleashes the benefits of PT for fuzzing via three novel techniques. First, PTrix introduces a scheme to highly parallel the processing of PT trace and target program execution. Second, it directly takes decoded PT trace as feedback for fuzzing, avoiding the expensive reconstruction of code coverage information. Third, PTrix maintains the new feedback with stronger feedback than edge-based code coverage, which helps reach new code space and defects that AFL may not. We evaluated PTrix by comparing its performance with the state-of-the-art fuzzers. Our results show that, given the same amount of time, PTrix achieves a significantly higher fuzzing speed and reaches into code regions missed by the other fuzzers. In addition, PTrix identifies 35 new vulnerabilities in a set of previously well-fuzzed binaries, showing its ability to complement existing fuzzers.