AI Safety

Inverse Abstraction of Neural Networks Using Symbolic Interpolation AAAI 2019 Is Everything Going According to Plan? Expectations in Goal Reasoning Agents AAAI 2019 Kernel-Based Reinforcement Learning in Robust Markov Decision Processes ICML 2019 Learning to Confuse: Generating Training Time Adversarial Data with Auto-Encoder NeurIPS 2019 Likelihood Ratios for Out-of-Distribution Detection NeurIPS 2019 Locate-Then-Detect: Real-time Web Attack Detection via Attention-based Deep Neural Networks IJCAI 2019 ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation ICML 2019 Monge blunts Bayes: Hardness Results for Adversarial Training ICML 2019 Moral Permissibility of Action Plans AAAI 2019 NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks ICML 2019 Once a MAN: Towards Multi-Target Attack via Learning Multi-Target Adversarial Network Once ICCV 2019 On the Sensitivity of Adversarial Robustness to Input Data Distributions ICLR 2019 PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks ICLR 2019 PopBots: Designing an Artificial Intelligence Curriculum for Early Childhood Education AAAI 2019 Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks NeurIPS 2019 Protecting Elections by Recounting Ballots IJCAI 2019 Protecting Neural Networks with Hierarchical Random Switching: Towards Better Robustness-Accuracy Trade-off for Stochastic Defenses IJCAI 2019 Provable Certificates for Adversarial Examples: Fitting a Ball in the Union of Polytopes NeurIPS 2019 Provable Robustness of ReLU networks via Maximization of Linear Regions AISTATS 2019 Provably robust boosted decision stumps and trees against adversarial attacks NeurIPS 2019 PROVEN: Verifying Robustness of Neural Networks with a Probabilistic Approach ICML 2019 Quality Control Attack Schemes in Crowdsourcing IJCAI 2019 RecurJac: An Efficient Recursive Algorithm for Bounding Jacobian Matrix of Neural Networks and Its Applications AAAI 2019 Reward Constrained Policy Optimization ICLR 2019 Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures ICLR 2019