Ashwin Ramesh Babu

Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters

2025 · Proceedings of the AAAI Conference on Artificial Intelligence

We present a Reinforcement Learning Platform for Adversarial Black-box untargeted and targeted attacks, RLAB, that allows users to select from various distortion filters to create adversarial examples. The platform uses a Reinforcement Learning agent to …