Image de couverture de livre

Repairing vulnerabilities without invisible hands. A differentiated replication study on LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Camporese, Maria, Massacci, Fabio
Format:	Preprint
Publié:	2025
Sujets:	Software Engineering Cryptography and Security Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Using ML filters to help automated vulnerability repairs: when it helps and when it doesn't
par: Camporese, Maria, et autres
Publié: (2025)

A Systematic Literature Review on Automated Exploit and Security Test Generation
par: Bui, Quang-Cuong, et autres
Publié: (2025)

Closing the Gap: A User Study on the Real-world Usefulness of AI-powered Vulnerability Detection & Repair in the IDE
par: Steenhoek, Benjamin, et autres
Publié: (2024)

ANVIL: Anomaly-based Vulnerability Identification without Labelled Training Data
par: Wang, Weizhou, et autres
Publié: (2024)

UniASM: Binary Code Similarity Detection without Fine-tuning
par: Gu, Yeming, et autres
Publié: (2022)

How Safe Are AI-Generated Patches? A Large-scale Study on Security Risks in LLM and Agentic Automated Program Repair on SWE-bench
par: Sajadi, Amirali, et autres
Publié: (2025)

From Lab to Reality: A Practical Evaluation of Deep Learning Models and LLMs for Vulnerability Detection
par: Lu, Chaomeng, et autres
Publié: (2025)

Evaluating and Improving the Robustness of Security Attack Detectors Generated by LLMs
par: Pasini, Samuele, et autres
Publié: (2024)

REBENCH: A Procedural, Fair-by-Construction Benchmark for LLMs on Stripped-Binary Types and Names (Extended Version)
par: Won, Jun Yeon, et autres
Publié: (2026)

Risks of ignoring uncertainty propagation in AI-augmented security pipelines
par: Mezzi, Emanuele, et autres
Publié: (2024)

"You still have to study" -- On the Security of LLM generated code
par: Goetz, Stefan, et autres
Publié: (2024)

Tady: A Neural Disassembler without Structural Constraint Violations
par: Qin, Siliang, et autres
Publié: (2025)

Assessing the Software Security Comprehension of Large Language Models
par: Siddiq, Mohammed Latif, et autres
Publié: (2025)

Beimingwu: A Learnware Dock System
par: Tan, Zhi-Hao, et autres
Publié: (2024)

MVD: A Multi-Lingual Software Vulnerability Detection Framework
par: Zhang, Boyu, et autres
Publié: (2024)

BertRLFuzzer: A BERT and Reinforcement Learning Based Fuzzer
par: Jha, Piyush, et autres
Publié: (2023)

A Study on Mixup-Inspired Augmentation Methods for Software Vulnerability Detection
par: Daneshvar, Seyed Shayan, et autres
Publié: (2025)

ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage
par: Liu, Chang, et autres
Publié: (2026)

A Manually-Curated Dataset of Fixes to Vulnerabilities of Open-Source Software
par: Ponta, Serena E., et autres
Publié: (2019)

SeBERTis: A Framework for Producing Classifiers of Security-Related Issue Reports
par: Masoumzadeh, Sogol, et autres
Publié: (2025)

A Modular Approach to Automatic Cyber Threat Attribution using Opinion Pools
par: Teuwen, Koen T. W.
Publié: (2024)

Security and Quality in LLM-Generated Code: A Multi-Language, Multi-Model Analysis
par: Kharma, Mohammed, et autres
Publié: (2025)

Code-Centric Detection of Vulnerability-Fixing Commits: A Unified Benchmark and Empirical Study
par: Loose, Nils, et autres
Publié: (2026)

A Large-Scale Exploit Instrumentation Study of AI/ML Supply Chain Attacks in Hugging Face Models
par: Casey, Beatrice, et autres
Publié: (2024)

LLMs for Qualitative Data Analysis Fail on Security-specificComments in Human Experiments
par: Camporese, Maria, et autres
Publié: (2026)

Deploying Privacy Guardrails for LLMs: A Comparative Analysis of Real-World Applications
par: Asthana, Shubhi, et autres
Publié: (2025)

RESCUE: Retrieval Augmented Secure Code Generation
par: Shi, Jiahao, et autres
Publié: (2025)

THEMIS: Towards Practical Intellectual Property Protection for Post-Deployment On-Device Deep Learning Models
par: Huang, Yujin, et autres
Publié: (2025)

Enhancing Cloud Security through Topic Modelling
par: Saleh, Sabbir M., et autres
Publié: (2025)

Alleviating Attack Data Scarcity: SCANIA's Experience Towards Enhancing In-Vehicle Cyber Security Measures
par: Sundfeldt, Frida, et autres
Publié: (2025)

Expanding ML-Documentation Standards For Better Security
par: Appel, Cara Ellen
Publié: (2025)

Fast, Fine-Grained Equivalence Checking for Neural Decompilers
par: Dramko, Luke, et autres
Publié: (2025)

XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants
par: Štorek, Adam, et autres
Publié: (2025)

From Trace to Line: LLM Agent for Real-World OSS Vulnerability Localization
par: Xi, Haoran, et autres
Publié: (2025)

From Coverage to Causes: Data-Centric Fuzzing for JavaScript Engines
par: Ganguly, Kishan Kumar, et autres
Publié: (2025)

EditLord: Learning Code Transformation Rules for Code Editing
par: Li, Weichen, et autres
Publié: (2025)

SecureInfer: Heterogeneous TEE-GPU Architecture for Privacy-Critical Tensors for Large Language Model Deployment
par: Nayan, Tushar, et autres
Publié: (2025)

AGNOMIN -- Architecture Agnostic Multi-Label Function Name Prediction
par: Achamyeleh, Yonatan Gizachew, et autres
Publié: (2025)

Rethinking the Evaluation of Secure Code Generation
par: Dai, Shih-Chieh, et autres
Publié: (2025)

Floating-Point Neural Network Verification at the Software Level
par: Manino, Edoardo, et autres
Publié: (2025)