AI Safety

Adversarial Parameter Attack on Deep Neural Networks ICML 2023 Adversarial Robustness in Discontinuous Spaces via Alternating Sampling & Descent WACV 2023 Adversarial Robustness through Random Weight Sampling NeurIPS 2023 Adversarial Robustness via Random Projection Filters CVPR 2023 Adversarial Text Generation by Search and Learning EMNLP 2023 Adversarial Textual Robustness on Visual Dialog ACL 2023 A Gradient Control Method for Backdoor Attacks on Parameter-Efficient Tuning ACL 2023 AI Audit: A Card Game to Reflect on Everyday AI Systems AAAI 2023 Among Us: Adversarially Robust Collaborative Perception by Consensus ICCV 2023 Analysis and Detectability of Offline Data Poisoning Attacks on Linear Dynamical Systems L4DC 2023 Analyzing Intentional Behavior in Autonomous Agents under Uncertainty IJCAI 2023 An Analysis of Robustness of Non-Lipschitz Networks JMLR 2023 A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints ICML 2023 An Embarrassingly Simple Backdoor Attack on Self-supervised Learning ICCV 2023 Anthropomorphization of AI: Opportunities and Risks EMNLP 2023 A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints NeurIPS 2023 Architectural Backdoors in Neural Networks CVPR 2023 Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems EMNLP 2023 Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark ACL 2023 A Rigorous Risk-aware Linear Approach to Extended Markov Ratio Decision Processes with Embedded Learning IJCAI 2023 A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks ICML 2023 A Robust Test for the Stationarity Assumption in Sequential Decision Making ICML 2023 A Semidefinite Relaxation Based Branch-and-Bound Method for Tight Neural Network Verification AAAI 2023 ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models EMNLP 2023 Asymmetric Certified Robustness via Feature-Convex Neural Networks NeurIPS 2023