Skip to content
NewA calmer, faster ZeroHour

AntiAgent cuts LLM vulnerability detections in JavaScript by 52.0-60.7%

Original title: Hardening JavaScript Programs against LLM-Based Vulnerability Detection

arXiv cs.CRby Zhenhao Tian ()1 min read
AI summary · x-ai/grok-4.7Summaries by Vani AI

Transformed programs still pass all project tests, and the extracted rules also transfer to Python and unseen vulnerability types.

AntiAgent hardens JavaScript before release so LLM vulnerability-detection agents are less likely to find flaws. It evolves a corpus of known-vulnerable programs, keeps versions the agent misses or misreports, and turns those changes into reusable rules. An LLM and the rules then adapt transformations to a new program while aiming to preserve semantics. Against four agents, including Claude Code and Codex, detections fall 52.0-60.7%, beating JS-Obfuscator and FPA.

Key facts
  • Rules stay effective on vulnerability types absent from the training corpus.
  • The method also works on programs written in Python.
  • Transformed programs pass all project tests in the evaluation.
  • AntiAgent outperforms JS-Obfuscator and FPA on every tested agent.
Analyze this story with Vani AIImpact, who is affected and what defenders should do, in a new chat

From the original article

1 min read at arxiv.org

JavaScript programs are often distributed as source code, so attackers can analyze them for vulnerabilities. LLM-based vulnerability detection agents now make this analysis much easier. To mitigate this emerging threat, we present AntiAgent, a defense that lets developers harden their programs against such detection agents.

arXiv cs.CR

By Zhenhao Tian · arxiv.org

Read the full article at arXiv cs.CR

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.