Copertina

Surgical Repair of Insecure Code Generation in LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sandoval, Gustavo, Dolan-Gavitt, Brendan, Garg, Siddharth
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

An Empirical Evaluation of LLMs for Solving Offensive Security Challenges
di: Shao, Minghao, et al.
Pubblicazione: (2024)

From Trace to Line: LLM Agent for Real-World OSS Vulnerability Localization
di: Xi, Haoran, et al.
Pubblicazione: (2025)

ELFuzz: Efficient Input Generation via LLM-driven Synthesis Over Fuzzer Space
di: Chen, Chuyang, et al.
Pubblicazione: (2025)

NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security
di: Shao, Minghao, et al.
Pubblicazione: (2024)

MetaCipher: A Time-Persistent and Universal Multi-Agent Framework for Cipher-Based Jailbreak Attacks for LLMs
di: Chen, Boyuan, et al.
Pubblicazione: (2025)

ARVO: Atlas of Reproducible Vulnerabilities for Open Source Software
di: Mei, Xiang, et al.
Pubblicazione: (2024)

Early Approaches to Adversarial Fine-Tuning for Prompt Injection Defense: A 2022 Study of GPT-3 and Contemporary Models
di: Sandoval, Gustavo, et al.
Pubblicazione: (2025)

On Benchmarking Code LLMs for Android Malware Analysis
di: He, Yiling, et al.
Pubblicazione: (2025)

ASCENT: Amplifying Power Side-Channel Resilience via Learning & Monte-Carlo Tree Search
di: Bhandari, Jitendra, et al.
Pubblicazione: (2024)

TruncFormer: Private LLM Inference Using Only Truncations
di: Yubeaton, Patrick, et al.
Pubblicazione: (2024)

CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
di: Shao, Minghao, et al.
Pubblicazione: (2025)

Model Cascading for Code: A Cascaded Black-Box Multi-Model Framework for Cost-Efficient Code Completion with Self-Testing
di: Chen, Boyuan, et al.
Pubblicazione: (2024)

Is The Watermarking Of LLM-Generated Code Robust?
di: Suresh, Tarun, et al.
Pubblicazione: (2024)

Scaling Trends for Data Poisoning in LLMs
di: Bowen, Dillon, et al.
Pubblicazione: (2024)

Patch Synthesis for Property Repair of Deep Neural Networks
di: Chi, Zhiming, et al.
Pubblicazione: (2024)

Improved Generation of Adversarial Examples Against Safety-aligned LLMs
di: Li, Qizhang, et al.
Pubblicazione: (2024)

Repairing vulnerabilities without invisible hands. A differentiated replication study on LLMs
di: Camporese, Maria, et al.
Pubblicazione: (2025)

(Security) Assertions by Large Language Models
di: Kande, Rahul, et al.
Pubblicazione: (2023)

On Design Principles for Private Adaptive Optimizers
di: Ganesh, Arun, et al.
Pubblicazione: (2025)

On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem
di: Pichler, Georg, et al.
Pubblicazione: (2024)

Improving LLM-Assisted Secure Code Generation through Retrieval-Augmented-Generation and Multi-Tool Feedback
di: Sriram, Vidyut, et al.
Pubblicazione: (2026)

Is API Access to LLMs Useful for Generating Private Synthetic Tabular Data?
di: Swanberg, Marika, et al.
Pubblicazione: (2025)

TFHE-Coder: Evaluating LLM-agentic Fully Homomorphic Encryption Code Generation
di: Kumar, Mayank, et al.
Pubblicazione: (2025)

Supporting Students in Navigating LLM-Generated Insecure Code
di: Park, Jaehwan, et al.
Pubblicazione: (2025)

Poisoned Source Code Detection in Code Models
di: Ghannoum, Ehab, et al.
Pubblicazione: (2025)

Can LLMs be Fooled? Investigating Vulnerabilities in LLMs
di: Abdali, Sara, et al.
Pubblicazione: (2024)

Bypassing Prompt Guards in Production with Controlled-Release Prompting
di: Fairoze, Jaiden, et al.
Pubblicazione: (2025)

Security-by-Design for LLM-Based Code Generation: Leveraging Internal Representations for Concept-Driven Steering Mechanisms
di: Wendlinger, Maximilian, et al.
Pubblicazione: (2026)

LLMStinger: Jailbreaking LLMs using RL fine-tuned LLMs
di: Jha, Piyush, et al.
Pubblicazione: (2024)

DeepProv: Behavioral Characterization and Repair of Neural Networks via Inference Provenance Graph Analysis
di: Hmida, Firas Ben, et al.
Pubblicazione: (2025)

Identifying Obfuscated Code through Graph-Based Semantic Analysis of Binary Code
di: Cohen, Roxane, et al.
Pubblicazione: (2025)

GNN-Based Code Annotation Logic for Establishing Security Boundaries in C Code
di: Gadey, Varun, et al.
Pubblicazione: (2024)

CodePurify: Defend Backdoor Attacks on Neural Code Models via Entropy-based Purification
di: Mu, Fangwen, et al.
Pubblicazione: (2024)

LMN: A Tool for Generating Machine Enforceable Policies from Natural Language Access Control Rules using LLMs
di: Sonune, Pratik, et al.
Pubblicazione: (2025)

Can LLMs Patch Security Issues?
di: Alrashedy, Kamel, et al.
Pubblicazione: (2023)

Excessive Reasoning Attack on Reasoning LLMs
di: Si, Wai Man, et al.
Pubblicazione: (2025)

Towards Watermarking of Open-Source LLMs
di: Gloaguen, Thibaud, et al.
Pubblicazione: (2025)

Entropy-Guided Attention for Private LLMs
di: Jha, Nandan Kumar, et al.
Pubblicazione: (2025)

Efficient Adversarial Training in LLMs with Continuous Attacks
di: Xhonneux, Sophie, et al.
Pubblicazione: (2024)

Instruction Backdoor Attacks Against Customized LLMs
di: Zhang, Rui, et al.
Pubblicazione: (2024)