AI Safety

ADBA: Approximation Decision Boundary Approach for Black-Box Adversarial Attacks AAAI 2025 Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models EMNLP 2025 A Detailed Factor Analysis for the Political Compass Test: Navigating Ideologies of Large Language Models IJCNLP 2025 ADU: Adaptive Detection of Unknown Categories in Black-Box Domain Adaptation CVPR 2025 AdvAgent: Controllable Blackbox Red-teaming on Web Agents ICML 2025 Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation IJCAI 2025 Advancing Oversight Reasoning across Languages for Audit Sycophantic Behaviour via X-Agent EMNLP 2025 AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations? ICCV 2025 Adversarial Attacks Against Automated Fact-Checking: A Survey EMNLP 2025 Adversarial Attacks on Data Attribution ICLR 2025 Adversarial-Inspired Backdoor Defense via Bridging Backdoor and Adversarial Attacks AAAI 2025 Adversarial Machine Unlearning ICLR 2025 Adversarial Preference Learning for Robust LLM Alignment ACL 2025 Adversarial Reasoning at Jailbreaking Time ICML 2025 Adversarial Robust Memory-Based Continual Learner ICCV 2025 Adversarial Robustness of Discriminative Self-Supervised Learning in Vision ICCV 2025 Adversarial Training for Defense Against Label Poisoning Attacks ICLR 2025 Adversarial Training for Probabilistic Robustness ICCV 2025 Adversaries Can Misuse Combinations of Safe Models ICML 2025 Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training EMNLP 2025 AdvERSEM: Adversarial Robustness Testing and Training of LLM-based Groundedness Evaluators via Semantic Structure Manipulation EMNLP 2025 AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs ICML 2025 AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models ICLR 2025 AEGIS2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails NAACL 2025 Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion Attacks AAAI 2025