Alexander Levine

adversarial robustness (6) randomized smoothing (5) certified robustness (4) adversarial defense (2) off-policy reinforcement learning (1) knowledge distillation (1) object detection (1) off-policy learning (1) data poisoning (1) curse of dimensionality (1) neyman-pearson lemma (1) adversarial attack (1) image manifold (1) generative model (1) adversarial training (1) reinforcement learning (1) adversarial perturbation (1) goal-conditioned reinforcement learning (1) adversarial patch attack (1) wasserstein distance (1)