AI Safety

Robust Decision Trees Against Adversarial Examples ICML 2019 Robustness of 3D Deep Learning in an Adversarial Setting CVPR 2019 Robustness Verification of Classification Deep Neural Networks via Linear Programming CVPR 2019 Robustra: Training Provable Robust Neural Networks over Reference Adversarial Space IJCAI 2019 Safe and Sample-Efficient Reinforcement Learning Algorithms for Factored Environments IJCAI 2019 Safe Convex Learning under Uncertain Constraints AISTATS 2019 Safe Exploration for Interactive Machine Learning NeurIPS 2019 Safe Policy Improvement with Baseline Bootstrapping in Factored Environments AAAI 2019 Sparse and Imperceivable Adversarial Attacks ICCV 2019 Teaching AI Agents Ethical Values Using Reinforcement Learning and Policy Orchestration IJCAI 2019 The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations IJCAI 2019 The Design of Human Oversight in Autonomous Weapon Systems IJCAI 2019 The Limitations of Adversarial Training and the Blind-Spot Attack ICLR 2019 Theoretical evidence for adversarial robustness through randomization NeurIPS 2019 Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers NeurIPS 2019 Towards Adversarially Robust Object Detection ICCV 2019 Towards Reliable Learning for High Stakes Applications AAAI 2019 Towards Robust ResNet: A Small Step but a Giant Leap IJCAI 2019 Towards the first adversarially robust neural network model on MNIST ICLR 2019 Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability ICLR 2019 Uniform Error Bounds for Gaussian Process Regression with Application to Safe Control NeurIPS 2019 Unlabeled Data Improves Adversarial Robustness NeurIPS 2019 VC Classes are Adversarially Robustly Learnable, but Only Improperly COLT 2019 Verifiable and Interpretable Reinforcement Learning through Program Synthesis AAAI 2019 Verification of Non-Linear Specifications for Neural Networks ICLR 2019