paperAugust 2026Unreviewed

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

Abstract

LLM customization platforms allow users to build task-specific models for code intelligence tasks by embedding instructions into system prompts, without modifying the underlying model parameters. While these platforms lower the barrier to developing customized LLMs, they also introduce a new attack surface: instruction backdoor attacks, in which adversaries implant hidden malicious behaviors into customized instructions. However, existing attacks suffer from two key limitations. First, they ofte

Framework mappings

OWASP Top 10 for LLM Applications

LLM04Data and Model Poisoning

MITRE ATLAS

AML.T0020Poison Training Data

NIST AI Risk Management Framework

MEASUREMeasure

Suggested from the entry's categories.

Cite

@misc{chen2026breaking,
  title = {{Breaking Customized LLMs for Coding: Automated Red Teaming for Instruction Backdoor Attacks}},
  author = {Yuchen Chen and Wei Cheng and Yuan Xiao and Wising Sun and Chunrong Fang and Yang Liu and Zhenyu Chen and Baowen Xu},
  year = {2026},
  month = aug,
  eprint = {2608.05659},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.05659}
}