AI Safety

Robustness of Graph Neural Networks at Scale NeurIPS 2021 Robust Reinforcement Learning: A Case Study in Linear Quadratic Regulation AAAI 2021 Safe Bayesian Optimisation for Controller Design by Utilising the Parameter Space Approach L4DC 2021 Safely Learning Dynamical Systems from Short Trajectories L4DC 2021 Safe Reinforcement Learning of Control-Affine Systems with Vertex Networks L4DC 2021 Safe Reinforcement Learning Using Advantage-Based Intervention ICML 2021 Safe Reinforcement Learning via Statistical Model Predictive Shielding RSS 2021 Safe Reinforcement Learning with Linear Function Approximation ICML 2021 Safety Analysis of Deep Neural Networks IJCAI 2021 Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learning RSS 2021 Safety Assurance for Systems with Machine Learning Components AAAI 2021 Sample Efficient Detection and Classification of Adversarial Attacks via Self-Supervised Embeddings ICCV 2021 Sample-Specific Output Constraints for Neural Networks AAAI 2021 Scalable Memory Protection in the PENGLAI Enclave OSDI 2021 Scaling the Convex Barrier with Active Sets ICLR 2021 Sequential Attacks on Kalman Filter-based Forward Collision Warning Systems AAAI 2021 Shift Invariance Can Reduce Adversarial Robustness NeurIPS 2021 SMT-based Safety Checking of Parameterized Multi-Agent Systems AAAI 2021 Stabilized Medical Image Attacks ICLR 2021 Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based Models ICLR 2021 Swiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark EMNLP 2021 Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits ICLR 2021 The Translucent Patch: A Physical and Universal Attack on Object Detectors CVPR 2021 Thinking Fast and Slow in AI AAAI 2021 Tightening Robustness Verification of Convolutional Neural Networks with Fine-Grained Linear Approximation AAAI 2021