AI Safety

Quantifying Memorization Across Neural Language Models ICLR 2023 Quantization-Aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks AAAI 2023 Query-Efficient Black-Box Red Teaming via Bayesian Optimization ACL 2023 Randomized Adversarial Training via Taylor Expansion CVPR 2023 Reachability Analysis of Neural Network Control Systems AAAI 2023 RealBehavior: A Framework for Faithfully Characterizing Foundation Models’ Human-like Behavior Mechanisms EMNLP 2023 Reconsidering Deception in Social Robotics: The Role of Human Vulnerability (Student Abstract) AAAI 2023 Redactor: A Data-Centric and Individualized Defense against Inference Attacks AAAI 2023 Red Teaming Deep Neural Networks with Feature Synthesis Tools NeurIPS 2023 Reliability Check: An Analysis of GPT-3’s Response to Sensitive Topics and Prompt Wording ACL 2023 Responsible Robotics: A Socio-Ethical Addition to Robotics Courses AAAI 2023 Rethinking Safe Control in the Presence of Self-Seeking Humans AAAI 2023 Revisiting the Assumption of Latent Separability for Backdoor Defenses ICLR 2023 Reward Gaming in Conditional Text Generation ACL 2023 RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical World ICCV 2023 RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural Prompts CVPR 2023 Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning NeurIPS 2023 Risk-Aware Decentralized Safe Control via Dynamic Responsibility Allocation (Student Abstract) AAAI 2023 Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners CoRL 2023 Robust Bayesian Satisficing NeurIPS 2023 Robust Contrastive Language-Image Pretraining against Data Poisoning and Backdoor Attacks NeurIPS 2023 Robust Evaluation of Diffusion-Based Adversarial Purification ICCV 2023 Robust Fair Clustering: A Novel Fairness Attack and Defense Framework ICLR 2023 Robust Multi-bit Natural Language Watermarking through Invariant Features ACL 2023 Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms ICLR 2023