PoCGen: Generating Proof-of-Concept Exploits for Vulnerabilities in Npm Packages
Deniz Simsek, Aryaz Eghbali, Michael Pradel

TL;DR
PoCGen is an innovative system that automatically generates and validates proof-of-concept exploits for npm package vulnerabilities by combining large language models with static and dynamic analysis, significantly aiding security patching efforts.
Contribution
PoCGen introduces a novel hybrid approach that integrates LLMs, static analysis, and dynamic validation to automate PoC exploit generation for npm vulnerabilities.
Findings
Successfully generates exploits for 77% of vulnerabilities in SecBench.js
Outperforms recent baseline by 45 percentage points
Generates exploits at an average cost of $0.02 each
Abstract
Security vulnerabilities in software packages are a significant concern for developers and users alike. Patching these vulnerabilities in a timely manner is crucial to restoring the integrity and security of software systems. However, previous work has shown that vulnerability reports often lack proof-of-concept (PoC) exploits, which are essential for fixing the vulnerability, testing patches, and avoiding regressions. Creating a PoC exploit is challenging because vulnerability reports are informal and often incomplete, and because it requires a detailed understanding of how inputs passed to potentially vulnerable APIs may reach security-relevant sinks. In this paper, we present PoCGen, a novel approach to autonomously generate and validate PoC exploits for vulnerabilities in npm packages. The approach is the first to address this task by combining the complementary strengths of large…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsWeb Application Security Vulnerabilities · Software Testing and Debugging Techniques · Information and Cyber Security
