Imagen de Portada

Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chang, Shuyu, Huang, Haiping, Zhang, Yanjun, Huang, Yujin, Xiao, Fu, Zhang, Leo Yu
Formato:	Preprint
Publicado:	2026
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

Defending Code Language Models against Backdoor Attacks with Deceptive Cross-Entropy Loss
por: Yang, Guang, et al.
Publicado: (2024)

Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements
por: Li, Yue, et al.
Publicado: (2026)

Backdoors in Code Summarizers: How Bad Is It?
por: Wang, Chenyu, et al.
Publicado: (2025)

Models Are Codes: Towards Measuring Malicious Code Poisoning Attacks on Pre-trained Model Hubs
por: Zhao, Jian, et al.
Publicado: (2024)

Semantic Consensus Decoding: Backdoor Defense for Verilog Code Generation
por: Yang, Guang, et al.
Publicado: (2026)

Demonstration Attack against In-Context Learning for Code Intelligence
por: Ge, Yifei, et al.
Publicado: (2024)

Exploring the Security Threats of Retriever Backdoors in Retrieval-Augmented Code Generation
por: Li, Tian, et al.
Publicado: (2025)

A Practical Adversarial Attack against Sequence-based Deep Learning Malware Classifiers
por: Tan, Kai, et al.
Publicado: (2025)

On the Adversarial Robustness of Instruction-Tuned Large Language Models for Code
por: Hossen, Md Imran, et al.
Publicado: (2024)

FDI: Attack Neural Code Generation Systems through User Feedback Channel
por: Sun, Zhensu, et al.
Publicado: (2024)

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

An Empirical Study on the Effectiveness of Large Language Models for Binary Code Understanding
por: Shang, Xiuwei, et al.
Publicado: (2025)

DeCoMa: Detecting and Purifying Code Dataset Watermarks through Dual Channel Code Abstraction
por: Xiao, Yuan, et al.
Publicado: (2025)

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

"Your AI, My Shell": Demystifying Prompt Injection Attacks on Agentic AI Coding Editors
por: Liu, Yue, et al.
Publicado: (2025)

Uncover the Premeditated Attacks: Detecting Exploitable Reentrancy Vulnerabilities by Identifying Attacker Contracts
por: Yang, Shuo, et al.
Publicado: (2024)

THEMIS: Towards Practical Intellectual Property Protection for Post-Deployment On-Device Deep Learning Models
por: Huang, Yujin, et al.
Publicado: (2025)

ROSA: Finding Backdoors with Fuzzing
por: Kokkonis, Dimitri, et al.
Publicado: (2025)

Detecting Stealthy Data Poisoning Attacks in AI Code Generators
por: Improta, Cristina
Publicado: (2025)

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

Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks
por: Qu, Yubin, et al.
Publicado: (2026)

CNT: Safety-oriented Function Reuse across LLMs via Cross-Model Neuron Transfer
por: Zhao, Yue, et al.
Publicado: (2026)

KEENHash: Hashing Programs into Function-Aware Embeddings for Large-Scale Binary Code Similarity Analysis
por: Liu, Zhijie, et al.
Publicado: (2025)

Constraint-based Adversarial Example Synthesis
por: Yu, Fang, et al.
Publicado: (2024)

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

Identifying Adversary Tactics and Techniques in Malware Binaries with an LLM Agent
por: Xuan, Zhou, et al.
Publicado: (2026)

Concerned with Data Contamination? Assessing Countermeasures in Code Language Model
por: Cao, Jialun, et al.
Publicado: (2024)

Constrained Decoding for Secure Code Generation
por: Fu, Yanjun, et al.
Publicado: (2024)

How Secure is Secure Code Generation? Adversarial Prompts Put LLM Defenses to the Test
por: Tessa, Melissa, et al.
Publicado: (2026)

GenSIaC: Toward Security-Aware Infrastructure-as-Code Generation with Large Language Models
por: Li, Yikun, et al.
Publicado: (2025)

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

An Adversarial Robust Behavior Sequence Anomaly Detection Approach Based on Critical Behavior Unit Learning
por: Zhan, Dongyang, et al.
Publicado: (2025)

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

GraphQLer: Enhancing GraphQL Security with Context-Aware API Testing
por: Tsai, Omar, et al.
Publicado: (2025)

Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol (MCP) Ecosystem
por: Song, Hao, et al.
Publicado: (2025)

MCGMark: An Encodable and Robust Online Watermark for Tracing LLM-Generated Malicious Code
por: Ning, Kaiwen, et al.
Publicado: (2024)

AutoVulnPHP: LLM-Powered Two-Stage PHP Vulnerability Detection and Automated Localization
por: Wang, Zhiqiang, et al.
Publicado: (2026)

Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study
por: Fu, Yujia, et al.
Publicado: (2023)

Killing Two Birds with One Stone: Malicious Package Detection in NPM and PyPI using a Single Model of Malicious Behavior Sequence
por: Zhang, Junan, et al.
Publicado: (2023)

CEBin: A Cost-Effective Framework for Large-Scale Binary Code Similarity Detection
por: Wang, Hao, et al.
Publicado: (2024)