Agent teams can be backdoored so that harmful behavior switches on only when peer evidence crosses a hidden threshold; a clean-data latent-transition filter can contain it.
InProceedings of the 2024 Conference on Empiri- calMethodsinNaturalLanguageProcessing,17889–17904
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When Collaboration Becomes a Trigger: Collective Evidence-Threshold Backdoors in Multi-Agent Systems
Agent teams can be backdoored so that harmful behavior switches on only when peer evidence crosses a hidden threshold; a clean-data latent-transition filter can contain it.