LLMs cannot reliably identify and reason about security vulnerabilities (yet?): a comprehensive evaluation, framework, and benchmarks

Files
llm-oakland2024.pdf(998.57 KB)
Accepted manuscript
Date
2024-05-19
DOI
10.1109/sp54263.2024.00210
Authors
Version
Accepted manuscript
URI
https://hdl.handle.net/2144/49910
OA Version
Citation
S. Ullah, M. Han, S. Pujar, H. Pearce, A. Coskun, G. Stringhini. 2024. "LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarks" 2024 IEEE Symposium on Security and Privacy (SP), pp.862-880. https://doi.org/10.1109/sp54263.2024.00210
Abstract
Description
License
Collections
BU Open Access Articles