Normative Conflicts and Shallow AI AlignmentPhilosophical Studies (Philos. Stud.), 2025 |
 Adversarial Attacks in Multimodal Systems: A Practitioner's SurveyAnnual International Computer Software and Applications Conference (COMPSAC), 2025 |
 Diff-Prompt: Diffusion-Driven Prompt Generator with Mask SupervisionInternational Conference on Learning Representations (ICLR), 2025 |
 QAVA: Query-Agnostic Visual Attack to Large Vision-Language ModelsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2025 |
 NLP Security and Ethics, in the WildTransactions of the Association for Computational Linguistics (TACL), 2025 |
 Shh, don't say that! Domain Certification in LLMsInternational Conference on Learning Representations (ICLR), 2025 |
