AI Safety

Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation EMNLP 2023 Mitigating Societal Harms in Large Language Models EMNLP 2023 Model Barrier: A Compact Un-Transferable Isolation Domain for Model Intellectual Property Protection CVPR 2023 Multi-Metrics Adaptively Identifies Backdoors in Federated Learning ICCV 2023 Multi-scale Diffusion Denoised Smoothing NeurIPS 2023 Multispectral Invisible Coating: Laminated Visible-Thermal Physical Attack against Multispectral Object Detectors Using Transparent Low-E Films AAAI 2023 Multi-step Jailbreaking Privacy Attacks on ChatGPT EMNLP 2023 Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation NeurIPS 2023 NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails EMNLP 2023 Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features NeurIPS 2023 Neural Policy Safety Verification via Predicate Abstraction: CEGAR AAAI 2023 Nichelle and Nancy: The Influence of Demographic Attributes and Tokenization Length on First Name Biases ACL 2023 NNSplitter: An Active Defense Solution for DNN Model via Automated Weight Obfuscation ICML 2023 NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models ACL 2023 One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training ICCV 2023 On Explaining Neural Network Robustness with Activation Path ICLR 2023 On the Adversarial Robustness of Out-of-distribution Generalization Models NeurIPS 2023 On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research EMNLP 2023 On the Exploitability of Instruction Tuning NeurIPS 2023 On the Forward Invariance of Neural ODEs ICML 2023 On the Sensitivity of Reward Inference to Misspecified Human Models ICLR 2023 On the Vulnerability of Backdoor Defenses for Federated Learning AAAI 2023 Optimizing over trained GNNs via symmetry breaking NeurIPS 2023 Out-of-Distribution Detection and Selective Generation for Conditional Language Models ICLR 2023 Out-of-Distribution Detection Is Not All You Need AAAI 2023