We present TrojDRL, a tool for exploring and evaluating backdoor attacks on deep reinforcement learning agents. TrojDRL exploits the sequential nature of deep reinforcement learning (DRL) and considers different gradations of threat models. We show that untargeted attacks on state-of-the-art actor-critic algorithms can circumvent existing defenses built on the assumption of backdoors being targeted. We evaluated TrojDRL on a broad set of DRL benchmarks and showed that the attacks require only poisoning as little as 0.025% of training data. Compared with existing works of backdoor attacks on classification models, TrojDRL provides a first step towards understanding the vulnerability of DRL agents.

No abstract

The advent of autonomous mobile multi-robot systems has driven innovation in both the industrial and defense sectors. The integration of such systems in safety-and securitycritical applications has raised concern over their resilience to attack. In this work, we investigate the security problem of a stealthy adversary masquerading as a properly functioning agent. We show that conventional multi-agent pathfinding solutions are vulnerable to these physical masquerade attacks. Furthermore, we provide a constraint-based formulation of multi-agent pathfinding that yields multi-agent plans that are provably resilient to physical masquerade attacks. This formalization leverages inter-agent observations to facilitate introspective monitoring to guarantee resilience.

No abstract

No abstract