AI Safety

Adaptive Risk Sensitive Model Predictive Control with Stochastic Search L4DC 2021 Admix: Enhancing the Transferability of Adversarial Attacks ICCV 2021 AdvDrop: Adversarial Attack to DNNs by Dropping Information ICCV 2021 Adversarial Attacks on Graph Classifiers via Bayesian Optimisation NeurIPS 2021 Adversarial Examples in Physical World IJCAI 2021 Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink CVPR 2021 Adversarially Robust Learning with Unknown Perturbation Sets COLT 2021 Adversarial Neuron Pruning Purifies Backdoored Deep Models NeurIPS 2021 Adversarial Robustness with Non-uniform Perturbations NeurIPS 2021 Adversarial Robustness with Semi-Infinite Constrained Learning NeurIPS 2021 Adversarial Training and Provable Robustness: A Tale of Two Objectives AAAI 2021 Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models ICCV 2021 AdvRush: Searching for Adversarially Robust Neural Architectures ICCV 2021 Agent Incentives: A Causal Perspective AAAI 2021 Aha! Adaptive History-Driven Attack for Decision-Based Black-Box Models ICCV 2021 A Law of Robustness for Two-Layers Neural Networks COLT 2021 Aligning AI With Shared Human Values ICLR 2021 An Empirical Study on Adversarial Attack on NMT: Languages and Positions Matter ACL 2021 Anti-Backdoor Learning: Training Clean Models on Poisoned Data NeurIPS 2021 A PAC-Bayes Analysis of Adversarial Robustness NeurIPS 2021 A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference ICLR 2021 A Separation Result Between Data-oblivious and Data-aware Poisoning Attacks NeurIPS 2021 Assisted Robust Reward Design CoRL 2021 Auditing Robot Learning for Safety and Compliance during Deployment CoRL 2021 Automated Discovery of Adaptive Attacks on Adversarial Defenses NeurIPS 2021