AI Safety

Topological Detection of Trojaned Neural Networks NeurIPS 2021 Towards a Unifying Framework for Formal Theories of Novelty AAAI 2021 Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons ICML 2021 Towards Evaluating and Training Verifiably Robust Neural Networks CVPR 2021 Towards Reducing Biases in Combining Multiple Experts Online IJCAI 2021 Towards Robustness of Deep Neural Networks via Regularization ICCV 2021 Towards Robust Neural Networks via Close-loop Control ICLR 2021 Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds NeurIPS 2021 Transfer Learning for Efficient Iterative Safety Validation AAAI 2021 Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution ACL 2021 Unifying Principles and Metrics for Safe and Assistive AI AAAI 2021 Value Alignment Verification ICML 2021 Verification and Repair of Neural Networks AAAI 2021 Verifying Reinforcement Learning up to Infinity IJCAI 2021 WaNet - Imperceptible Warping-based Backdoor Attack ICLR 2021 When does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning? NeurIPS 2021 Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching ICLR 2021 Achieving 100Gbps Intrusion Prevention on a Single Server OSDI 2020 Adaptive Reward-Poisoning Attacks against Reinforcement Learning ICML 2020 Adversarially Robust Distillation AAAI 2020 Adversarially Robust Streaming Algorithms via Differential Privacy NeurIPS 2020 Adversarially robust transfer learning ICLR 2020 Adversarial Separation Network for Speaker Recognition Interspeech 2020 Adversarial Training and Provable Defenses: Bridging the Gap ICLR 2020 Adversarial Weight Perturbation Helps Robust Generalization NeurIPS 2020