AI Safety

Adversary for Social Good: Protecting Familial Privacy through Joint Adversarial Attacks AAAI 2020 A Gamified Assessment Platform for Predicting the Risk of Dementia +Parkinson’s disease (DPD) Co-Morbidity IJCAI 2020 A Geometry-Inspired Attack for Generating Natural Language Adversarial Examples COLING 2020 Algorithmic recourse under imperfect causal knowledge: a probabilistic approach NeurIPS 2020 A Multi-Objective Approach to Mitigate Negative Side Effects IJCAI 2020 A Self-supervised Approach for Adversarial Robustness CVPR 2020 Asymptotically Unambitious Artificial General Intelligence AAAI 2020 A Target-Agnostic Attack on Deep Models: Exploiting Security Vulnerabilities of Transfer Learning ICLR 2020 Attack of the Tails: Yes, You Really Can Backdoor Federated Learning NeurIPS 2020 Attacks Which Do Not Kill Training Make Adversarial Learning Stronger ICML 2020 Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond NeurIPS 2020 Avoiding Side Effects By Considering Future Tasks NeurIPS 2020 Backpropagating Linearly Improves Transferability of Adversarial Examples NeurIPS 2020 BayesOpt Adversarial Attack ICLR 2020 Black-box Certification and Learning under Adversarial Perturbations ICML 2020 Branch and Bound for Piecewise Linear Neural Network Verification JMLR 2020 Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness ICLR 2020 BullStop: A Mobile App for Cyberbullying Prevention COLING 2020 Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings ICML 2020 Certifiably Adversarially Robust Detection of Out-of-Distribution Data NeurIPS 2020 Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing ICLR 2020 Certifying Confidence via Randomized Smoothing NeurIPS 2020 Consequences of Misaligned AI NeurIPS 2020 Consistency Regularization for Certified Robustness of Smoothed Classifiers NeurIPS 2020 Constrained Markov Decision Processes via Backward Value Functions ICML 2020