A Survey on Reinforcement Learning Security with Application to Autonomous Driving

no code implementations • 12 Dec 2022 • Ambra Demontis, Maura Pintor, Luca Demetrio, Kathrin Grosse, Hsiao-Ying Lin, Chengfang Fang, Battista Biggio, Fabio Roli

Reinforcement learning allows machines to learn from their own experience.

Autonomous Driving reinforcement-learning +1

DAFAR: Defending against Adversaries by Feedback-Autoencoder Reconstruction

no code implementations • 11 Mar 2021 • Haowen Liu, Ping Yi, Hsiao-Ying Lin, Jie Shi, Weidong Qiu

We propose DAFAR, a feedback framework that allows deep learning models to detect/purify adversarial examples in high effectiveness and universality, with low area and time overhead.