Cover Image

Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilities

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Simin, He, Yixin, Jana, Suman, Ray, Baishakhi
Format:	Preprint
Published:	2025
Subjects:	Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

REFINE: Enhancing Program Repair Agents through Context-Aware Patch Refinement
by: Pabba, Anvith, et al.
Published: (2025)

Your Compiler is Backdooring Your Model: Understanding and Exploiting Compilation Inconsistency Vulnerabilities in Deep Learning Compilers
by: Chen, Simin, et al.
Published: (2025)

SemAgent: A Semantics Aware Program Repair Agent
by: Pabba, Anvith, et al.
Published: (2025)

FaultLine: Automated Proof-of-Vulnerability Generation Using LLM Agents
by: Nitin, Vikram, et al.
Published: (2025)

Trustworthy AI Software Engineers
by: Aleti, Aldeida, et al.
Published: (2026)

Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination
by: Chen, Simin, et al.
Published: (2025)

Patch Validation in Automated Vulnerability Repair
by: Yu, Zheng, et al.
Published: (2026)

Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study
by: Ceka, Ira, et al.
Published: (2025)

ComPass: Contrastive Learning for Automated Patch Correctness Assessment in Program Repair
by: Zhang, Quanjun, et al.
Published: (2026)

When Automated Program Repair Meets Regression Testing -- An Extensive Study on 2 Million Patches
by: Lou, Yiling, et al.
Published: (2021)

Agentic AI Software Engineers: Programming with Trust
by: Roychoudhury, Abhik, et al.
Published: (2025)

SpecTra: Enhancing the Code Translation Ability of Language Models by Generating Multi-Modal Specifications
by: Nitin, Vikram, et al.
Published: (2024)

From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair
by: Li, Chenglin, et al.
Published: (2026)

UTFix: Change Aware Unit Test Repairing using LLM
by: Rahman, Shanto, et al.
Published: (2025)

When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?
by: Peng, Yibo, et al.
Published: (2025)

EvoRepair: Enhancing Vulnerability Repair Agents Through Experience-Based Self-Evolution
by: Hu, Haichuan, et al.
Published: (2026)

PatchRecall: Patch-Driven Retrieval for Automated Program Repair
by: Dihan, Mahir Labib, et al.
Published: (2026)

Agent That Debugs: Dynamic State-Guided Vulnerability Repair
by: Liu, Zhengyao, et al.
Published: (2025)

Accelerating Patch Validation for Program Repair with Interception-Based Execution Scheduling
by: Xiao, Yuan-An, et al.
Published: (2023)

Learning to Focus: Context Extraction for Efficient Code Vulnerability Detection with Language Models
by: Zheng, Xinran, et al.
Published: (2025)

A Case Study of LLM for Automated Vulnerability Repair: Assessing Impact of Reasoning and Patch Validation Feedback
by: Kulsum, Ummay, et al.
Published: (2024)

Yuga: Automatically Detecting Lifetime Annotation Bugs in the Rust Language
by: Nitin, Vikram, et al.
Published: (2023)

BlueCodeAgent: A Blue Teaming Agent Enabled by Automated Red Teaming for CodeGen AI
by: Guo, Chengquan, et al.
Published: (2025)

CodeSense: a Real-World Benchmark and Dataset for Code Semantic Reasoning
by: Roy, Monoshi Kumar, et al.
Published: (2025)

Vulnerability Detection with Code Language Models: How Far Are We?
by: Ding, Yangruibo, et al.
Published: (2024)

Beyond Crash-to-Patch: Patch Evolution for Linux Kernel Repair
by: Bai, Luyao, et al.
Published: (2026)

MultiMend: Multilingual Program Repair with Context Augmentation and Multi-Hunk Patch Generation
by: Gharibi, Reza, et al.
Published: (2025)

PatchZero: Zero-Shot Automatic Patch Correctness Assessment
by: Zhou, Xin, et al.
Published: (2023)

Enhancing Automated Program Repair via Faulty Token Localization and Quality-Aware Patch Refinement
by: Kong, Jiaolong, et al.
Published: (2025)

C2SaferRust: Transforming C Projects into Safer Rust with NeuroSymbolic Techniques
by: Nitin, Vikram, et al.
Published: (2025)

RepairAgent: An Autonomous, LLM-Based Agent for Program Repair
by: Bouzenia, Islem, et al.
Published: (2024)

ITER: Iterative Neural Repair for Multi-Location Patches
by: Ye, He, et al.
Published: (2023)

Improving Data Curation of Software Vulnerability Patches through Uncertainty Quantification
by: Chen, Hui, et al.
Published: (2024)

Towards Causal Deep Learning for Vulnerability Detection
by: Rahman, Md Mahbubur, et al.
Published: (2023)

On the Evaluation of Large Language Models in Multilingual Vulnerability Repair
by: wang, Dong, et al.
Published: (2025)

When Large Language Models Confront Repository-Level Automatic Program Repair: How Well They Done?
by: Chen, Yuxiao, et al.
Published: (2024)

Revisiting Vulnerability Patch Localization: An Empirical Study and LLM-Based Solution
by: Xu, Haoran, et al.
Published: (2025)

Veritas: A Semantically Grounded Agentic Framework for Memory Corruption Vulnerability Detection in Binaries
by: Zheng, Xinran, et al.
Published: (2026)

When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair
by: Luo, Wenqiang, et al.
Published: (2024)

PathFix: Automated Program Repair with Expected Path
by: He, Xu, et al.
Published: (2025)