{
  "id": 16158,
  "url": "https://arxiv.org/abs/2608.01085v1",
  "title": "When Collaboration Becomes a Trigger: Collective Evidence-Threshold Backdoors in Multi-Agent Systems",
  "summary": "LLM-based multi-agent systems (MAS) extend LLM capabilities through iterative communication and shared contexts. However, this collaboration introduces a vulnerability: backdoor behavior can be activated when peer evidence reaches a hidden threshold, rather than being determined by any single message. We introduce a collective evidence-threshold backdoor paradigm for MAS and Boundary-Conditioned Backdoor Injection (BCBI), which constructs counterfactual boundary pairs to separate benign behavior",
  "authors": "Jia-Hao Xiao, Lei Feng, Min-Ling Zhang",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-02T08:38:44.000Z",
  "fetched_at": "2026-08-04T05:10:21.797Z",
  "source_slug": "arxiv-cslg",
  "source_name": "arXiv cs.LG",
  "source_homepage": "https://arxiv.org/list/cs.LG/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/16158",
  "original_url": "https://arxiv.org/abs/2608.01085v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}