{
  "id": 17387,
  "url": "https://arxiv.org/abs/2608.05659v1",
  "title": "Breaking Customized LLMs for Coding: Automated Red Teaming for Instruction Backdoor Attacks",
  "summary": "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",
  "authors": "Yuchen Chen, Wei Cheng, Yuan Xiao, Wising Sun, Chunrong Fang, Yang Liu, Zhenyu Chen, Baowen Xu",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-06T06:57:10.000Z",
  "fetched_at": "2026-08-07T05:10:58.501Z",
  "source_slug": "x-arxiv-red-teaming-query",
  "source_name": "arXiv red teaming query",
  "source_homepage": "https://arxiv.org/a/redteam",
  "ethics_ai_record_url": "https://ethics.ai/record/17387",
  "original_url": "https://arxiv.org/abs/2608.05659v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}