When Collaboration Becomes a Trigger: Collective Evidence-Threshold Backdoors in Multi-Agent Systems
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
Record details
Published: 2 August 2026
Source: arXiv cs.LG
Category: Research
Topics: Agents & autonomy
Retrieved: 4 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
What Could the Agent See at 19:05? Generating Temporal Enterprise Scenarios from Real Research and Replaying Them to Evaluate Agents
arXiv cs.HC · 2 August 2026
From AI Technical Debt to Agentic Technical Debt: A Systematic Mapping of Root Causes and Manifestations in Agentic AI Systems
arXiv cs.CR (AI security) · 2 August 2026
IR222: From Cyberwar to Killer Robots: Emerging Technology and International Security
LSE Data Science Institute · 2 August 2026
Scoring Rules! Statistical and Strategic Alignment for Text Evaluation Metrics
arXiv cs.LG · 2 August 2026
Douyin Multimodal Embedding Model Technical Report
HuggingFace Daily Papers · 2 August 2026
Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills
HuggingFace Daily Papers · 2 August 2026
How to cite this record
ethics.ai (2 August 2026), “When Collaboration Becomes a Trigger: Collective Evidence-Threshold Backdoors in Multi-Agent Systems,” evidence record 16158, https://ethics.ai/record/16158 (originally published by arXiv cs.LG).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.