AI Safety

The Perils of Learning From Unlabeled Data: Backdoor Attacks on Semi-supervised Learning ICCV 2023 The Perils of Trial-and-Error Reward Design: Misdesign through Overfitting and Invalid Task Specifications AAAI 2023 The Resource Problem of Using Linear Layer Leakage Attack in Federated Learning CVPR 2023 The Troubling Emergence of Hallucination in Large Language Models - An Extensive Definition, Quantification, and Prescriptive Remediations EMNLP 2023 The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data ICCV 2023 Thorny Roses: Investigating the Dual Use Dilemma in Natural Language Processing EMNLP 2023 TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored Models ICCV 2023 Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learning CoRL 2023 Toward Robust Diagnosis: A Contour Attention Preserving Adversarial Defense for COVID-19 Detection AAAI 2023 Towards Building More Robust Models with Frequency Bias ICCV 2023 Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration CVPR 2023 Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition CVPR 2023 Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly NeurIPS 2023 Towards General Error Diagnosis via Behavioral Testing in Machine Translation EMNLP 2023 Towards Reliable Neural Specifications ICML 2023 Towards Robust Model Watermark via Reducing Parametric Vulnerability ICCV 2023 Towards Robustness Certification Against Universal Perturbations ICLR 2023 Towards Safe AI: Sandboxing DNNs-Based Controllers in Stochastic Games AAAI 2023 Towards Safe Reinforcement Learning via OOD Dynamics Detection in Autonomous Driving System (Student Abstract) AAAI 2023 Towards Stable Backdoor Purification through Feature Shift Tuning NeurIPS 2023 Toward Stronger Textual Attack Detectors EMNLP 2023 Towards Verifying the Geometric Robustness of Large-Scale Neural Networks AAAI 2023 ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation EMNLP 2023 Toxicity in chatgpt: Analyzing persona-assigned language models EMNLP 2023 Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence ICCV 2023