Safety

Toward Exploratory Inverse Constraint Inference with Generative Diffusion Verifiers ICLR 2025 Towards More General Video-based Deepfake Detection through Facial Component Guided Adaptation for Foundation Model CVPR 2025 TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis ACL 2025 Understanding Constraint Inference in Safety-Critical Inverse Reinforcement Learning ICLR 2025 Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights ACL 2025 Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models ACL 2025 Verification of Neural Networks Against Convolutional Perturbations via Parameterised Kernels AAAI 2025 VestaBench: An Embodied Benchmark for Safe Long-Horizon Planning Under Multi-Constraint and Adversarial Settings EMNLP 2025 VLSBench: Unveiling Visual Leakage in Multimodal Safety ACL 2025 VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration ACL 2025 What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs ACL 2025 Where's the Liability in the Generative Era? Recovery-based Black-Box Detection of AI-Generated Content CVPR 2025 Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement ACL 2025 Accelerating Adversarially Robust Model Selection for Deep Neural Networks via Racing AAAI 2024 A Chinese Dataset for Evaluating the Safeguards in Large Language Models ACL 2024 AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents NeurIPS 2024 A Huber Loss Minimization Approach to Byzantine Robust Federated Learning AAAI 2024 All Languages Matter: On the Multilingual Safety of LLMs ACL 2024 ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs ACL 2024 ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings EMNLP 2024 Athena: Safe Autonomous Agents with Verbal Contrastive Learning EMNLP 2024 Backdoor Defense via Test-Time Detecting and Repairing CVPR 2024 BaitAttack: Alleviating Intention Shift in Jailbreak Attacks via Adaptive Bait Crafting EMNLP 2024 Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation AAAI 2024 Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression EMNLP 2024