all InfoSec news
Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning. (arXiv:2205.14842v2 [cs.LG] UPDATED)
cs.CR updates on arXiv.org arxiv.org
We study reward poisoning attacks on online deep reinforcement learning
(DRL), where the attacker is oblivious to the learning algorithm used by the
agent and the dynamics of the environment. We demonstrate the intrinsic
vulnerability of state-of-the-art DRL algorithms by designing a general,
black-box reward poisoning framework called adversarial MDP attacks. We
instantiate our framework to construct two new attacks which only corrupt the
rewards for a small fraction of the total training timesteps and make the agent
learn a …
agent algorithm algorithms art attacks box called environment framework general oblivious poisoning state study vulnerability