Safety

VeriCompress: A Tool to Streamline the Synthesis of Verified Robust Compressed Neural Networks from Scratch AAAI 2024 Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy AAAI 2024 WebOlympus: An Open Platform for Web Agents on Live Websites EMNLP 2024 What Makes and Breaks Safety Fine-tuning? A Mechanistic Study NeurIPS 2024 Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models EMNLP 2024 Advances in AI for Safety, Equity, and Well-Being on Web and Social Media: Detection, Robustness, Attribution, and Mitigation AAAI 2023 ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models EMNLP 2023 AutoCost: Evolving Intrinsic Cost for Zero-Violation Reinforcement Learning AAAI 2023 Can Large Language Models Safely Address Patient Questions Following Cataract Surgery? ACL 2023 CEM: Constrained Entropy Maximization for Task-Agnostic Safe Exploration AAAI 2023 Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning AAAI 2023 Characterizing the Optimal $0-1$ Loss for Multi-class Classification with a Test-time Attacker NeurIPS 2023 Combining Runtime Monitoring and Machine Learning with Human Feedback AAAI 2023 Correct-by-Construction Reinforcement Learning of Cardiac Pacemakers from Duration Calculus Requirements AAAI 2023 Defending against Insertion-based Textual Backdoor Attacks via Attribution ACL 2023 Evaluating Model-Free Reinforcement Learning toward Safety-Critical Tasks AAAI 2023 Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Models EMNLP 2023 GTA: Gated Toxicity Avoidance for LM Performance Preservation EMNLP 2023 Guarded Policy Optimization with Imperfect Online Demonstrations ICLR 2023 Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs Through a Global Prompt Hacking Competition EMNLP 2023 InstructSafety: A Unified Framework for Building Multidimensional and Explainable Safety Detector through Instruction Tuning EMNLP 2023 Language Detoxification with Attribute-Discriminative Latent Space ACL 2023 MIL-Decoding: Detoxifying Language Models at Token-Level via Multiple Instance Learning ACL 2023 Multi-Agent First Order Constrained Optimization in Policy Space NeurIPS 2023 On the Robustness of Safe Reinforcement Learning under Observational Perturbations ICLR 2023