AI Safety

TrapDoc: Deceiving LLM Users by Injecting Imperceptible Phantom Tokens into Documents EMNLP 2025 TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling EMNLP 2025 TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis ACL 2025 TrojanDec: Data-free Detection of Trojan Inputs in Self-supervised Learning AAAI 2025 TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent EMNLP 2025 TrojanWave: Exploiting Prompt Learning for Stealthy Backdoor Attacks on Large Audio-Language Models EMNLP 2025 Trust Me, I’m Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer EMNLP 2025 TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models ICML 2025 Trustworthy Machine Learning through Data-Specific Indistinguishability ICML 2025 TUBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning ACL 2025 Tuning-Free Accountable Intervention for LLM Deployment – a Metacognitive Approach AAAI 2025 TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice NAACL 2025 Turning Logic Against Itself: Probing Model Defenses Through Contrastive Questions EMNLP 2025 TWIST: Text-encoder Weight-editing for Inserting Secret Trojans in Text-to-Image Models ACL 2025 UCSC at SemEval-2025 Task 3: Context, Models and Prompt Optimization for Automated Hallucination Detection in LLM Output SemEval 2025 UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning ICML 2025 uMedSum: A Unified Framework for Clinical Abstractive Summarization ACL 2025 UMUTeam at SemEval-2025 Task 3: Detecting Hallucinations in Multilingual Texts Using Encoder-only Models Guided by Large Language Models SemEval 2025 Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failures CoRL 2025 Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models ICCV 2025 Uncovering Gaps in How Humans and LLMs Interpret Subjective Language ICLR 2025 Undermining Mental Proof: How AI Can Make Cooperation Harder by Making Thinking Easier AAAI 2025 Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron ICLR 2025 Understanding and Enhancing the Transferability of Jailbreaking Attacks ICLR 2025 Understanding and Meeting Practitioner Needs When Measuring Representational Harms Caused by LLM-Based Systems ACL 2025