CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities
This addresses the need for a real-world cybersecurity benchmark for AI agents, which is crucial for assessing threats to web applications, though it is incremental as it builds on existing vulnerability data.
The paper tackles the problem of evaluating large language model agents' ability to exploit real-world web application vulnerabilities by introducing CVE-Bench, a benchmark based on critical-severity CVEs, and finds that state-of-the-art agents can resolve up to 13% of vulnerabilities.
Large language model (LLM) agents are increasingly capable of autonomously conducting cyberattacks, posing significant threats to existing applications. This growing risk highlights the urgent need for a real-world benchmark to evaluate the ability of LLM agents to exploit web application vulnerabilities. However, existing benchmarks fall short as they are limited to abstracted Capture the Flag competitions or lack comprehensive coverage. Building a benchmark for real-world vulnerabilities involves both specialized expertise to reproduce exploits and a systematic approach to evaluating unpredictable threats. To address this challenge, we introduce CVE-Bench, a real-world cybersecurity benchmark based on critical-severity Common Vulnerabilities and Exposures. In CVE-Bench, we design a sandbox framework that enables LLM agents to exploit vulnerable web applications in scenarios that mimic real-world conditions, while also providing effective evaluation of their exploits. Our evaluation shows that the state-of-the-art agent framework can resolve up to 13% of vulnerabilities.