Llms Cannot Reliably Identify And Reason About Security Vulnerabilities (yet?): A Comprehensive Evaluation, Framework, And Benchmarks
Saad Ullah, Mingji Han, Saurabh Pujar, Hammond Pearce, Ayse Coskun, Gianluca Stringhini . 2024 IEEE Symposium on Security and Privacy (SP) 2024 – 43 citations
[Paper]
Large Language Models (LLMs) have been suggested for use in automated
vulnerability repair, but benchmarks showing they can consistently identify
security-related bugs are lacking. We thus develop SecLLMHolmes, a fully
automated evaluation framework that performs the most detailed investigation to
date on whether LLMs can reliably identify and reason about security-related
bugs. We construct a set of 228 code scenarios and analyze eight of the most
capable LLMs across eight different investigative dimensions using our
framework. Our evaluation shows LLMs provide non-deterministic responses,
incorrect and unfaithful reasoning, and perform poorly in real-world scenarios.
Most importantly, our findings reveal significant non-robustness in even the
most advanced models like PaLM2' and GPT-4’: by merely changing function or
variable names, or by the addition of library functions in the source code,
these models can yield incorrect answers in 26% and 17% of cases, respectively.
These findings demonstrate that further LLM advances are needed before LLMs can
be used as general purpose security assistants.