AI Safety

Robustness of Bayesian Neural Networks to Gradient-Based Attacks NeurIPS 2020 Robustness to Programmable String Transformations via Augmented Abstract Training ICML 2020 Robustness Verification for Transformers ICLR 2020 Safe non-smooth black-box optimization with application to policy search L4DC 2020 Safe Policy Learning for Continuous Control CoRL 2020 SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutions ACL 2020 Safe Reinforcement Learning in Constrained Markov Decision Processes ICML 2020 Safe Reinforcement Learning via Curriculum Induction NeurIPS 2020 Sampling-based Reachability Analysis: A Random Set Theory Approach with Adversarial Sampling CoRL 2020 Security Analysis of Safe and Seldonian Reinforcement Learning Algorithms NeurIPS 2020 Sign Bits Are All You Need for Black-Box Attacks ICLR 2020 Strategic Classification is Causal Modeling in Disguise ICML 2020 TBT: Targeted Neural Network Attack With Bit Trojan CVPR 2020 Toward Operational Safety Verification of AI-Enabled CPS (Student Abstract) AAAI 2020 Towards Adversarially Robust Knowledge Graph Embeddings AAAI 2020 Towards Certificated Model Robustness Against Weight Perturbations AAAI 2020 Towards Controllable Biases in Language Generation EMNLP 2020 Towards neural networks that provably know when they don't know ICLR 2020 Towards Safe Policy Improvement for Non-Stationary MDPs NeurIPS 2020 Towards Socially Responsible AI: Cognitive Bias-Aware Multi-Objective Learning AAAI 2020 Towards Stable and Efficient Training of Verifiably Robust Neural Networks ICLR 2020 Towards Trustable Explainable AI IJCAI 2020 Transferable Calibration with Lower Bias and Variance in Domain Adaptation NeurIPS 2020 Uncertainty-Aware Constraint Learning for Adaptive Safe Motion Planning from Demonstrations CoRL 2020 Weight Poisoning Attacks on Pretrained Models ACL 2020