Amoeba: Circumventing ML-supported Network Censorship via Adversarial Reinforcement Learning

1 code implementation • 31 Oct 2023 • Haoyu Liu, Alec F. Diallo, Paul Patras

Specifically, we cast the problem of finding adversarial flows that will be misclassified as a sequence generation task, which we solve with Amoeba, a novel reinforcement learning algorithm that we design.

Adversarial Attack reinforcement-learning