# Patch2Vuln: Agentic Reconstruction of Vulnerabilities from Linux Distribution Binary Patches

arXiv: https://arxiv.org/abs/2605.06601 · HTML: https://mlsanity.com/paper/2605.06601/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 31 references that are in the map.
- First posted on arXiv 7 May 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 8 of 8)

- [LLM Agents can Autonomously Exploit One-day Vulnerabilities](https://mlsanity.com/paper/2404.08144/) (2024)
- [PentestGPT: An LLM-empowered Automatic Penetration Testing Tool](https://mlsanity.com/paper/2308.06782/) (2023)
- [Teams of LLM Agents can Exploit Zero-Day Vulnerabilities](https://mlsanity.com/paper/2406.01637/) (2024)
- [Neural Network-based Graph Embedding for Cross-Platform Binary Code Similarity Detection](https://mlsanity.com/paper/1708.06525/) (2017)
- [EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities](https://mlsanity.com/paper/2409.16165/) (2024)
- [SAFE: Self-Attentive Function Embeddings for Binary Similarity](https://mlsanity.com/paper/1811.05296/) (2018)
- [Multi-Agent Penetration Testing AI for the Web](https://mlsanity.com/paper/2508.20816/) (2025)
- [Towards Optimal Agentic Architectures for Offensive Security Tasks](https://mlsanity.com/paper/2604.18718/) (2026)

## Abstract (arXiv)

Security updates create a short but important window in which defenders and attackers can compare vulnerable and patched software. Yet in many operational settings, the most accessible artifacts are binary packages rather than source patches or advisory text. This paper asks whether a language-model agent, restricted to local binary-derived evidence, can reconstruct the security meaning of Linux distribution updates. Patch2Vuln is a local, resumable pipeline that extracts old/new ELF pairs, diffs them with Ghidra and Ghidriff, ranks changed functions, builds candidate dossiers, and asks an offline agent to produce a preliminary audit, bounded validation plan, and final audit. We evaluate Patch2Vuln on 25 Ubuntu `.deb` package pairs: 20 security-update pairs and five negative controls, all manually adjudicated against private source-patch and binary-function ground truth. The agent localizes a verified security-relevant patch function in 10 of 20 security pairs and assigns an accepted final root-cause class in 11 of 20. Oracle diagnostics show that six security pairs fail before model reasoning because the binary differ or ranker omits the right function, with one additional context-export miss. A separate bounded validation pass produces two target-level minimized behavioral old/new differentials, both for tcpdump, but no crash, timeout, sanitizer finding, or memory-corruption proof; all five negative controls are classified as unknown and produce no validation differentials. These results support agentic vulnerability reconstruction from binary patches as a useful research target while showing that binary-diff coverage and local behavioral validation remain the limiting components.