Minimalistic attacks: how little it takes to fool deep reinforcement learning policies

Recent studies have revealed that neural-network-based policies can be easily fooled by adversarial examples. However, while most prior works analyze the effects of perturbing every pixel of every frame assuming white-box policy access, in this article, we take a more restrictive view toward adversary generation - with the goal of unveiling the limits of a model's vulnerability. In particular, we explore minimalistic attacks by defining three key settings: 1) Black-Box Policy Access: where the attacker only has access to the input (state) and output (action probability) of an RL policy; 2) Fractional-State Adversary: where only several pixels are perturbed, with the extreme case being a single-pixel adversary; and 3) Tactically Chanced Attack: where only significant frames are tactically chosen to be attacked. We formulate the adversarial attack by accommodating the three key settings, and explore their potency on six Atari games by examining four fully trained state-of-the-art policies. In Breakout, for example, we surprisingly find that: 1) all policies showcase significant performance degradation by merely modifying 0.01% of the input state and 2) the policy trained by DQN is totally deceived by perturbing only 1% frames.