A single poisoned agent, triggered by a spatiotemporal movement pattern and trained with a hacked reward, can drive a whole cooperative multi-agent team to failure while keeping clean performance nearly unchanged.
Optimized computation offloading performance in virtual edge computing systems via deep reinforcement learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
BLAST: A Stealthy Backdoor Leverage Attack against Cooperative Multi-Agent Deep Reinforcement Learning based Systems
A single poisoned agent, triggered by a spatiotemporal movement pattern and trained with a hacked reward, can drive a whole cooperative multi-agent team to failure while keeping clean performance nearly unchanged.