P2Patch: Exploit-Guided Vulnerability Repair
cs.CR, cs.AI, cs.SE
Submitted: 2026-10-14
Updated: 2026-10-14
Comments: 25 pages, 6 figures, 13 tables. M. Iranmanesh and S. Moradi Sabet contributed equally. Code: https://github.com/P2Patch/P2patch
Code: https://github.com/P2Patch/P2patch
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- PoC-Gym: Towards More Reliable LLM-Assisted Proof-of-Concept Exploit Generation
- CodeCureAgent: Automatic Classification and Repair of Static Analysis Warnings
- Characteristics, Root Causes, and Detection of Incomplete Security Bug Fixes in the Linux Kernel
- FaultLine: Automated Proof-of-Vulnerability Generation Using LLM Agents
- From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEs
- VulnRepairEval: An Exploit-Based Evaluation Framework for Assessing Large Language Model Vulnerability Repair Capabilities
- PATCHEVAL: A New Benchmark for Evaluating LLMs on Patching Real-World Vulnerabilities
- Patch Validation in Automated Vulnerability Repair
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Estimating the Social Cost of Corporate Data Breaches
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills