Announcement_1
We demonstrate both theoretically and empirically that Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injection can effectively mislead popular algorithms like UCB and Thompson Sampling with minimal attack cost.
We demonstrate both theoretically and empirically that Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injection can effectively mislead popular algorithms like UCB and Thompson Sampling with minimal attack cost.