AI Safety

Lipschitz regularity of deep neural networks: analysis and efficient estimation NeurIPS 2018 Minimax-Regret Querying on Side Effects for Safe Optimality in Factored Markov Decision Processes IJCAI 2018 Mitigating Adversarial Effects Through Randomization ICLR 2018 Mitigating Bias in Adaptive Data Gathering via Differential Privacy ICML 2018 Nickel: A Framework for Design and Verification of Information Flow Control Systems OSDI 2018 Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples ICML 2018 Online Learning with an Unknown Fairness Metric NeurIPS 2018 On the Utility of Lay Summaries and AI Safety Disclosures: Toward Robust, Open Research Oversight NAACL 2018 PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples ICLR 2018 Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks NeurIPS 2018 Predictive Uncertainty Estimation via Prior Networks NeurIPS 2018 Probabilistically Safe Robot Planning with Confidence-Based Human Predictions RSS 2018 Probabilistic Verification for Obviously Strategyproof Mechanisms IJCAI 2018 Reachability Analysis of Deep Neural Networks with Provable Guarantees IJCAI 2018 Semidefinite relaxations for certifying robustness to adversarial examples NeurIPS 2018 Stagewise Safe Bayesian Optimization with Gaussian Processes ICML 2018 Stochastic Activation Pruning for Robust Adversarial Defense ICLR 2018 Synthesizing Robust Adversarial Examples ICML 2018 The effect of information controls on developers in China: An analysis of censorship in Chinese open source projects COLING 2018 The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamical Systems CoRL 2018 Thermometer Encoding: One Hot Way To Resist Adversarial Examples ICLR 2018 The Uncertainty Bellman Equation and Exploration ICML 2018 Towards Deep Learning Models Resistant to Adversarial Attacks ICLR 2018 Towards Fast Computation of Certified Robustness for ReLU Networks ICML 2018 Two Sides of the Same Coin: Belief Revision and Enforcing Arguments IJCAI 2018