Imagen de Portada

When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Peng, Yibo, Song, James, Li, Lei, Yang, Xinyu, Christodorescu, Mihai, Mangal, Ravi, Pasareanu, Corina, Zheng, Haizhong, Chen, Beidi
Formato:	Preprint
Publicado:	2025
Materias:	Cryptography and Security Software Engineering
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SecCodePRM: A Process Reward Model for Code Security
por: Yu, Weichen, et al.
Publicado: (2026)

A Mixture of Linear Corrections Generates Secure Code
por: Yu, Weichen, et al.
Publicado: (2025)

On the Difficulty of Selecting Few-Shot Examples for Effective LLM-based Vulnerability Detection
por: Hannan, Md Abdul, et al.
Publicado: (2025)

Taint-Style Vulnerability Detection and Confirmation for Node.js Packages Using LLM Agent Reasoning
por: Ni, Ronghao, et al.
Publicado: (2026)

Zero-Permission Manipulation: Can We Trust Large Multimodal Model Powered GUI Agents?
por: Qian, Yi, et al.
Publicado: (2026)

Similar but Patched Code Considered Harmful -- The Impact of Similar but Patched Code on Recurring Vulnerability Detection and How to Remove Them
por: Tan, Zixuan, et al.
Publicado: (2024)

Clawed and Dangerous: Can We Trust Open Agentic Systems?
por: Chen, Shiping, et al.
Publicado: (2026)

A Slicing-Based Approach for Detecting and Patching Vulnerable Code Clones
por: Alomari, Hakam, et al.
Publicado: (2025)

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems
por: Wang, Su, et al.
Publicado: (2026)

SCRIBE: Practical Static Binary Patching via Binary-Aware Recompilation of Decompiled Code
por: Dai, Han, et al.
Publicado: (2026)

From LLMs to Agents: A Comparative Evaluation of LLMs and LLM-based Agents in Security Patch Detection
por: Han, Junxiao, et al.
Publicado: (2025)

AVDA: Autonomous Vibe Detection Authoring for Cybersecurity
por: Bulut, Fatih, et al.
Publicado: (2026)

LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?
por: Liu, Bin, et al.
Publicado: (2025)

Toward Quantum-Safe Software Engineering: A Vision for Post-Quantum Cryptography Migration
por: Zhang, Lei
Publicado: (2026)

PatchFuzz: Patch Fuzzing for JavaScript Engines
por: Wang, Junjie, et al.
Publicado: (2025)

Lockbox -- A Zero Trust Architecture for Secure Processing of Sensitive Cloud Workloads
por: Thotempudi, Vamshi Krishna, et al.
Publicado: (2026)

FidelityGPT: Correcting Decompilation Distortions with Retrieval Augmented Generation
por: Zhou, Zhiping, et al.
Publicado: (2025)

How Far Have We Gone in Binary Code Understanding Using Large Language Models
por: Shang, Xiuwei, et al.
Publicado: (2024)

Skills as Verifiable Artifacts: A Trust Schema and a Biconditional Correctness Criterion for Human-in-the-Loop Agent Runtimes
por: Metere, Alfredo
Publicado: (2026)

Beyond Trusting Trust: Multi-Model Validation for Robust Code Generation
por: McDanel, Bradley
Publicado: (2025)

When Labels Are Scarce: A Systematic Mapping of Label-Efficient Code Vulnerability Detection
por: Khalal, Noor, et al.
Publicado: (2026)

Optimal Circuit Synthesis of Linear Codes for Error Detection and Correction
por: Yang, Xi, et al.
Publicado: (2026)

A Taxonomy of Functional Security Features and How They Can Be Located
por: Hermann, Kevin, et al.
Publicado: (2025)

Residual Risk Analysis in Benign Code: How Far Are We? A Multi-Model Semantic and Structural Similarity Approach
por: Farhad, Mohammad, et al.
Publicado: (2026)

HYDRA: A Hybrid Heuristic-Guided Deep Representation Architecture for Predicting Latent Zero-Day Vulnerabilities in Patched Functions
por: Farhad, Mohammad, et al.
Publicado: (2025)

Exploiting LLM Agent Supply Chains via Payload-less Skills
por: Liu, Xinyu, et al.
Publicado: (2026)

Inferring Properties of Graph Neural Networks
por: Nguyen, Dat, et al.
Publicado: (2024)

Can I Check What I Designed? Mapping Security Design DSLs to Code Analyzers
por: Peldszus, Sven, et al.
Publicado: (2026)

Revisiting Vulnerability Patch Identification on Data in the Wild
por: Irsan, Ivana Clairine, et al.
Publicado: (2026)

Accelerating Automatic Program Repair with Dual Retrieval-Augmented Fine-Tuning and Patch Generation on Large Language Models
por: Guo, Hanyang, et al.
Publicado: (2025)

What You Trust Is Insecure: Demystifying How Developers (Mis)Use Trusted Execution Environments in Practice
por: Niu, Yuqing, et al.
Publicado: (2025)

An Investigation of Patch Porting Practices of the Linux Kernel Ecosystem
por: Li, Xingyu, et al.
Publicado: (2024)

SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
por: Hu, Qi, et al.
Publicado: (2026)

Empirical Study of Code Large Language Models for Binary Security Patch Detection
por: Li, Qingyuan, et al.
Publicado: (2025)

Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets
por: Xiao, Yuan, et al.
Publicado: (2026)

A Systematic Study of LLM-Based Architectures for Automated Patching
por: Xu, Qingxiao, et al.
Publicado: (2026)

PPT4J: Patch Presence Test for Java Binaries
por: Pan, Zhiyuan, et al.
Publicado: (2023)

ARAP: Demystifying Anti Runtime Analysis Code in Android Apps
por: Suo, Dewen, et al.
Publicado: (2024)

Securing the Software Package Supply Chain for Critical Systems
por: Murali, Ritwik, et al.
Publicado: (2025)

FuzzAgent: Multi-Agent System for Evolutionary Library Fuzzing
por: Lyu, Yunlong, et al.
Publicado: (2026)