AI Safety

Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks JMLR 2021 Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database AAAI 2021 Probabilistic robust linear quadratic regulators with Gaussian processes L4DC 2021 Probabilistic Robustness Quantification of Neural Networks AAAI 2021 ProFlip: Targeted Trojan Attack With Progressive Bit Flips ICCV 2021 Provably Efficient Actor-Critic for Risk-Sensitive and Robust Adversarial RL: A Linear-Quadratic Case AISTATS 2021 Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learning NeurIPS 2021 Provably robust classification of adversarial examples with detection ICLR 2021 Provably Safe and Efficient Motion Planning with Uncertain Human Dynamics RSS 2021 Provably Safe PAC-MDP Exploration Using Analogies AISTATS 2021 Pushing the Right Buttons: Adversarial Evaluation of Quality Estimation EMNLP 2021 Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes NeurIPS 2021 Query Complexity of Adversarial Attacks ICML 2021 Random Noise Defense Against Query-Based Black-Box Attacks NeurIPS 2021 RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models EMNLP 2021 Recent Advances in Adversarial Training for Adversarial Robustness IJCAI 2021 Recovering AES Keys with a Deep Cold Boot Attack ICML 2021 Reinforcement Learning Under Moral Uncertainty ICML 2021 Reliability Testing for Natural Language Processing Systems ACL 2021 Rethinking Stealthiness of Backdoor Attack against NLP Models ACL 2021 Robot Reinforcement Learning on the Constraint Manifold CoRL 2021 Robust and Private Learning of Halfspaces AISTATS 2021 Robust Bayesian Neural Networks by Spectral Expectation Bound Regularization CVPR 2021 Robust learning under clean-label attack COLT 2021 Robustness Certification for Point Cloud Models ICCV 2021