Most plasticity interventions in DRL reduce backdoor attack success rates while SAM increases them via gradient amplification; the work introduces an SCC framework and loss-sharpness detection indicator.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning
Most plasticity interventions in DRL reduce backdoor attack success rates while SAM increases them via gradient amplification; the work introduces an SCC framework and loss-sharpness detection indicator.