Adaptive Discounting of Training Time Attacks
This work addresses security vulnerabilities in RL systems by enabling stronger constructive training-time attacks, which is incremental as it builds on prior C-TTA research.
The paper tackles the problem of training-time attacks in reinforcement learning by developing a method to force un-adoptable target behaviors on a victim agent, achieving efficient attacks with dynamic planning horizons.
Among the most insidious attacks on Reinforcement Learning (RL) solutions are training-time attacks (TTAs) that create loopholes and backdoors in the learned behaviour. Not limited to a simple disruption, constructive TTAs (C-TTAs) are now available, where the attacker forces a specific, target behaviour upon a training RL agent (victim). However, even state-of-the-art C-TTAs focus on target behaviours that could be naturally adopted by the victim if not for a particular feature of the environment dynamics, which C-TTAs exploit. In this work, we show that a C-TTA is possible even when the target behaviour is un-adoptable due to both environment dynamics as well as non-optimality with respect to the victim objective(s). To find efficient attacks in this context, we develop a specialised flavour of the DDPG algorithm, which we term gammaDDPG, that learns this stronger version of C-TTA. gammaDDPG dynamically alters the attack policy planning horizon based on the victim's current behaviour. This improves effort distribution throughout the attack timeline and reduces the effect of uncertainty the attacker has about the victim. To demonstrate the features of our method and better relate the results to prior research, we borrow a 3D grid domain from a state-of-the-art C-TTA for our experiments. Code is available at "bit.ly/github-rb-gDDPG".