Cover Image

An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yan, Shenao, Wang, Shen, Duan, Yue, Hong, Hanbin, Lee, Kiho, Kim, Doowon, Hong, Yuan
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Artificial Intelligence Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning
by: Yan, Shenao, et al.
Published: (2026)

Towards Personalizing Secure Programming Education with LLM-Injected Vulnerabilities
by: Frazier, Matthew, et al.
Published: (2026)

How Code Representation Shapes False-Positive Dynamics in Cross-Language LLM Vulnerability Detection
by: Chen, Maofei, et al.
Published: (2026)

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

Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation
by: Chang, Shuyu, et al.
Published: (2026)

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

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

CleanVul: Automatic Function-Level Vulnerability Detection in Code Commits Using LLM Heuristics
by: Li, Yikun, et al.
Published: (2024)

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

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

MegaVul: A C/C++ Vulnerability Dataset with Comprehensive Code Representation
by: Ni, Chao, et al.
Published: (2024)

Black-Box Adversarial Attacks on LLM-Based Code Completion
by: Jenko, Slobodan, et al.
Published: (2024)

Triggering and Detecting Exploitable Library Vulnerability from the Client by Directed Greybox Fuzzing
by: Zhao, Yukai, et al.
Published: (2026)

Towards Robust Detection of Open Source Software Supply Chain Poisoning Attacks in Industry Environments
by: Zheng, Xinyi, et al.
Published: (2024)

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

A Systematic Evaluation of Parameter-Efficient Fine-Tuning Methods for the Security of Code LLMs
by: Lee, Kiho, et al.
Published: (2025)

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

IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities
by: Li, Ziyang, et al.
Published: (2024)

Unsupervised Binary Code Translation with Application to Code Similarity Detection and Vulnerability Discovery
by: Ahmad, Iftakhar, et al.
Published: (2024)

StagedVulBERT: Multi-Granular Vulnerability Detection with a Novel Pre-trained Code Model
by: Jiang, Yuan, et al.
Published: (2024)

Impact of Code Transformation on Detection of Smart Contract Vulnerabilities
by: Manh, Cuong Tran, et al.
Published: (2024)

Needles at Scale: LLM-Assisted Target Selection for Windows Vulnerability Research
by: Bommarito II, Michael J.
Published: (2026)

LLM-based Vulnerability Discovery through the Lens of Code Metrics
by: Weissberg, Felix, et al.
Published: (2025)

Towards Demystifying and Repairing LLM-in-the-Loop Vulnerabilities
by: Ma, Yujie, et al.
Published: (2026)

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

Is GitHub's Copilot as Bad as Humans at Introducing Vulnerabilities in Code?
by: Asare, Owura, et al.
Published: (2022)

Lightweight Vulnerability Detection from Code Metrics and Token Features
by: Chiu, Chun Yin
Published: (2026)

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

A Comparison of Vulnerability Feature Extraction Methods from Textual Attack Patterns
by: Othman, Refat, et al.
Published: (2024)

An Empirical Study of Vulnerable Package Dependencies in LLM Repositories
by: Liu, Shuhan, et al.
Published: (2025)

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

OpDiffer: LLM-Assisted Opcode-Level Differential Testing of Ethereum Virtual Machine
by: Ma, Jie, et al.
Published: (2025)

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

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

Assessing Vulnerability in Smart Contracts: The Role of Code Complexity Metrics in Security Analysis
by: Tehrani, Masoud Jamshidiyan
Published: (2024)

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

Execution-State-Aware LLM Reasoning for Automated Proof-of-Vulnerability Generation
by: Li, Haoyu, et al.
Published: (2026)

XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants
by: Štorek, Adam, et al.
Published: (2025)

LLM Security Guard for Code
by: Kavian, Arya, et al.
Published: (2024)