AI Safety

Safety-Aware Preference-Based Learning for Safety-Critical Control L4DC 2022 Safety Guarantees for Neural Network Dynamic Systems via Stochastic Barrier Functions NeurIPS 2022 SafetyKit: First Aid for Measuring Safety in Open-domain Conversational Systems ACL 2022 Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation ICML 2022 Segment and Complete: Defending Object Detectors Against Adversarial Patch Attacks With Robust Patch Detection CVPR 2022 Self-Healing Robust Neural Networks via Closed-Loop Control JMLR 2022 Shield Decentralization for Safe Multi-Agent Reinforcement Learning NeurIPS 2022 Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch NeurIPS 2022 Stability Verification in Stochastic Control Systems via Neural Network Supermartingales AAAI 2022 Task-Relevant Failure Detection for Trajectory Predictors in Autonomous Vehicles CoRL 2022 Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks EMNLP 2022 Textual Manifold-based Defense Against Natural Language Adversarial Examples EMNLP 2022 The Battlefront of Combating Misinformation and Coping with Media Bias AACL 2022 The King Is Naked: On the Notion of Robustness for Natural Language Processing AAAI 2022 The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems ACL 2022 Threat Scenarios and Best Practices to Detect Neural Fake News COLING 2022 Tight Neural Network Verification via Semidefinite Relaxations and Linear Reformulations AAAI 2022 To Trust or Not To Trust Prediction Scores for Membership Inference Attacks IJCAI 2022 Toward Robust Spiking Neural Network Against Adversarial Perturbation NeurIPS 2022 Towards Class-Oriented Poisoning Attacks Against Neural Networks WACV 2022 Towards Evaluating the Robustness of Neural Networks Learned by Transduction ICLR 2022 Towards Practical Certifiable Patch Defense With Vision Transformer CVPR 2022 Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk IJCAI 2022 Towards Safe Reinforcement Learning with a Safety Editor Policy NeurIPS 2022 Training OOD Detectors in their Natural Habitats ICML 2022