Buchumschlag

Code Security Vulnerability Repair Using Reinforcement Learning with Large Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Islam, Nafis Tanveer, Karkevandi, Mohammad Bahrami, Najafirad, Peyman
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Cryptography and Security Artificial Intelligence Software Engineering
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

LLM-Powered Code Vulnerability Repair with Reinforcement Learning and Semantic Reward
von: Islam, Nafis Tanveer, et al.
Veröffentlicht: (2024)

Can Reinforcement Learning Unlock the Hidden Dangers in Aligned Large Language Models?
von: Karkevandi, Mohammad Bahrami, et al.
Veröffentlicht: (2024)

Unintentional Security Flaws in Code: Automated Defense via Root Cause Analysis
von: Islam, Nafis Tanveer, et al.
Veröffentlicht: (2024)

Enhancing Source Code Security with LLMs: Demystifying The Challenges and Generating Reliable Repairs
von: Islam, Nafis Tanveer, et al.
Veröffentlicht: (2024)

AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing
von: Nunez, Ana, et al.
Veröffentlicht: (2024)

Enhancing Reverse Engineering: Investigating and Benchmarking Large Language Models for Vulnerability Analysis in Decompiled Binaries
von: Manuel, Dylan, et al.
Veröffentlicht: (2024)

An Unbiased Transformer Source Code Learning with Semantic Vulnerability Graph
von: Islam, Nafis Tanveer, et al.
Veröffentlicht: (2023)

Poisoning Programs by Un-Repairing Code: Security Concerns of AI-generated Code
von: Improta, Cristina
Veröffentlicht: (2024)

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

SecureFixAgent: A Hybrid LLM Agent for Automated Python Static Vulnerability Repair
von: Gajjar, Jugal, et al.
Veröffentlicht: (2025)

From Detection to Prevention: Explaining Security-Critical Code to Avoid Vulnerabilities
von: Krishnamurthy, Ranjith, et al.
Veröffentlicht: (2026)

Smart-LLaMA-DPO: Reinforced Large Language Model for Explainable Smart Contract Vulnerability Detection
von: Yu, Lei, et al.
Veröffentlicht: (2025)

LLbezpeky: Leveraging Large Language Models for Vulnerability Detection
von: Mathews, Noble Saji, et al.
Veröffentlicht: (2024)

Broken by Default: A Formal Verification Study of Security Vulnerabilities in AI-Generated Code
von: Blain, Dominik, et al.
Veröffentlicht: (2026)

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models
von: Bruni, Marc, et al.
Veröffentlicht: (2025)

MalCodeAI: Autonomous Vulnerability Detection and Remediation via Language Agnostic Code Reasoning
von: Gajjar, Jugal, et al.
Veröffentlicht: (2025)

Traces of Memorisation in Large Language Models for Code
von: Al-Kaswan, Ali, et al.
Veröffentlicht: (2023)

Securing Smart Contract Languages with a Unified Agentic Framework for Vulnerability Repair in Solidity and Move
von: Karanjai, Rabimba, et al.
Veröffentlicht: (2025)

Harnessing Large Language Models for Software Vulnerability Detection: A Comprehensive Benchmarking Study
von: Tamberg, Karl, et al.
Veröffentlicht: (2024)

VulDetectBench: Evaluating the Deep Capability of Vulnerability Detection with Large Language Models
von: Liu, Yu, et al.
Veröffentlicht: (2024)

SAEL: Leveraging Large Language Models with Adaptive Mixture-of-Experts for Smart Contract Vulnerability Detection
von: Yu, Lei, et al.
Veröffentlicht: (2025)

How Effective Are Neural Networks for Fixing Security Vulnerabilities
von: Wu, Yi, et al.
Veröffentlicht: (2023)

Large Language Model Supply Chain: Open Problems From the Security Perspective
von: Hu, Qiang, et al.
Veröffentlicht: (2024)

Learning to Generate Secure Code via Token-Level Rewards
von: Quan, Jiazheng, et al.
Veröffentlicht: (2026)

Harnessing the Power of LLMs in Source Code Vulnerability Detection
von: Mahyari, Andrew A
Veröffentlicht: (2024)

QLPro: Automated Code Vulnerability Discovery via LLM and Static Code Analysis Integration
von: Hu, Junze, et al.
Veröffentlicht: (2025)

The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation
von: Zhang, Xiaoyu, et al.
Veröffentlicht: (2025)

MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents
von: Steinberg, Jonathan, et al.
Veröffentlicht: (2026)

Smart-LLaMA: Two-Stage Post-Training of Large Language Models for Smart Contract Vulnerability Detection and Explanation
von: Yu, Lei, et al.
Veröffentlicht: (2024)

Leveraging Large Language Models for Command Injection Vulnerability Analysis in Python: An Empirical Study on Popular Open-Source Projects
von: Wang, Yuxuan, et al.
Veröffentlicht: (2025)

Causative Insights into Open Source Software Security using Large Language Code Embeddings and Semantic Vulnerability Graph
von: Islam, Nafis Tanveer, et al.
Veröffentlicht: (2024)

DUALGUAGE: Automated Joint Security-Functionality Benchmarking for Secure Code Generation
von: Pathak, Abhijeet, et al.
Veröffentlicht: (2025)

Towards Secure Logging: Characterizing and Benchmarking Logging Code Security Issues with LLMs
von: Yuan, He Yang, et al.
Veröffentlicht: (2026)

AI Code Generators for Security: Friend or Foe?
von: Natella, Roberto, et al.
Veröffentlicht: (2024)

LLM4CVE: Enabling Iterative Automated Vulnerability Repair with Large Language Models
von: Fakih, Mohamad, et al.
Veröffentlicht: (2025)

An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection
von: Yan, Shenao, et al.
Veröffentlicht: (2024)

AgenticSCR: An Autonomous Agentic Secure Code Review for Immature Vulnerabilities Detection
von: Charoenwet, Wachiraphan, et al.
Veröffentlicht: (2026)

Fortifying LLM-Based Code Generation with Graph-Based Reasoning on Secure Coding Practices
von: Patir, Rupam, et al.
Veröffentlicht: (2025)

CodeHacker: Automated Test Case Generation for Detecting Vulnerabilities in Competitive Programming Solutions
von: Shi, Jingwei, et al.
Veröffentlicht: (2026)

Security of LLM-generated Code: A Comparative Analysis
von: Morkonda, Srivathsan G, et al.
Veröffentlicht: (2026)