AI Safety

Constrained Policy Optimization ICML 2017 Counterfactual Fairness NeurIPS 2017 Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation NeurIPS 2017 From Automation to Autonomous Systems: A Legal Phenomenology with Problems of Accountability IJCAI 2017 Generalizing GANs: A Turing Perspective NeurIPS 2017 Inverse Reward Design NeurIPS 2017 Lower bounds on the robustness to adversarial perturbations NeurIPS 2017 Modeling Bias Reduction Strategies in a Biased Agent IJCAI 2017 On Automating the Doctrine of Double Effect IJCAI 2017 Privacy and Autonomous Systems IJCAI 2017 Strong Inconsistency in Nonmonotonic Reasoning IJCAI 2017 Strongly-Typed Agents are Guaranteed to Interact Safely ICML 2017 The Off-Switch Game IJCAI 2017 Light-Weight Contexts: An OS Abstraction for Safety and Performance OSDI 2016 A Comprehensive Survey on Safe Reinforcement Learning JMLR 2015 Bad Universal Priors and Notions of Optimality COLT 2015 Is Feature Selection Secure against Training Data Poisoning? ICML 2015 Preserving Privacy of Continuous High-dimensional Data with Minimax Filters AISTATS 2015 The Security of Latent Dirichlet Allocation AISTATS 2015 On Provably Safe Obstacle Avoidance for Autonomous Robotic Ground Vehicles RSS 2013 Burn-in, bias, and the rationality of anchoring NeurIPS 2012 Robustness and risk-sensitivity in Markov decision processes NeurIPS 2012 Security Analysis of Online Centroid Anomaly Detection JMLR 2012 Tractable Objectives for Robust Policy Optimization NeurIPS 2012 Safety Evaluation of Physical Human-Robot Interaction via Crash-Testing RSS 2007