Lying with the truth: open-channel multi-agent collusion manipulates beliefs via Generative Montage

The paper proposes a cognitive collusion attack where multiple agents collaboratively publish only fragments of true information on public channels, inducing victim agents to form false beliefs. The authors propose the Generative Montage framework, where three roles—Writer, Editor, Director—generate and rank evidence fragments through adversarial debate, then distribute them via Sybil accounts. On the CoPHEME dataset built from PHEME, the attack success rate across 14 model families reaches 74.4% (closed-source) and 70.6% (open-weight); reasoning-enhanced open-weight models are more susceptible than base models, while closed-source models show the opposite trend, with explicit CoT prompting increasing ASR by 3.1% and 4.7%, respectively. The downstream judge's deception rate exceeds 60%, and ablation studies show that degrading to a single agent reduces ASR to 26.8%.

Deep readingGenerating