DGBA enables reliable backdoor attacks on real-world RL policies under partial observability by learning stochastic visual triggers via conditional diffusion and using advantage-based poisoning at critical states.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
When Backdoors Meet Partial Observability: Attacking Real-World Reinforcement Learning
DGBA enables reliable backdoor attacks on real-world RL policies under partial observability by learning stochastic visual triggers via conditional diffusion and using advantage-based poisoning at critical states.
- Hint Tuning: Less Data Makes Better Reasoners