AI Safety

Generating High-Quality Explanations for Navigation in Partially-Revealed Environments NeurIPS 2021 Globally-Robust Neural Networks ICML 2021 Hidden Cost of Randomized Smoothing AISTATS 2021 High Confidence Generalization for Reinforcement Learning ICML 2021 HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training With Crafted Input Noise ICCV 2021 How Robust Are Randomized Smoothing Based Defenses to Data Poisoning? CVPR 2021 Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoods NeurIPS 2021 Improved, Deterministic Smoothing for L_1 Certified Robustness ICML 2021 Improving Adversarial Robustness via Channel-wise Activation Suppressing ICLR 2021 Improving the Transferability of Adversarial Samples With Adversarial Transformations CVPR 2021 Improving VAEs' Robustness to Adversarial Attack ICLR 2021 Indecision Modeling AAAI 2021 Infinite Time Horizon Safety of Bayesian Neural Networks NeurIPS 2021 Initiative Defense against Facial Manipulation AAAI 2021 Integer-Arithmetic-Only Certified Robustness for Quantized Neural Networks ICCV 2021 Inverse Constrained Reinforcement Learning ICML 2021 Inverse Reinforcement Learning From Like-Minded Teachers AAAI 2021 Investigating Robustness of Dialog Models to Popular Figurative Language Constructs EMNLP 2021 Is the Most Accurate AI the Best Teammate? Optimizing AI for Teamwork AAAI 2021 Justicia: A Stochastic SAT Approach to Formally Verify Fairness AAAI 2021 Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks ICML 2021 Learnable Boundary Guided Adversarial Training ICCV 2021 Learning Approximate Forward Reachable Sets Using Separating Kernels L4DC 2021 Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations NeurIPS 2021 Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs NeurIPS 2021