Breaking Customized LLMs for Coding: Automated Red Teaming for Instruction Backdoor Attacks
Yuchen Chen, Wei Cheng, Yuan Xiao, Wising Sun, Chunrong Fang, Yang Liu, Zhenyu Chen, Baowen Xu
cs.CR
Submitted: 2026-08-06
Comments: Accepted to the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Rethinking the Evaluation of Secure Code Generation
- A Survey on Code Generation with LLM-based Agents
- Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
- BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
- DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs
- A Survey on Large Language Models for Code Generation
- A Systematic Literature Review on Detecting Software Vulnerabilities with Large Language Models
- AutoBackdoor: Automating Backdoor Attacks via LLM Agents
- CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation
- Let the Trial Begin: A Mock-Court Approach to Vulnerability Detection using LLM-Based Agents
- GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
- Instruction Tuning for Large Language Models: A Survey
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Estimating the Social Cost of Corporate Data Breaches
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills