Interpretable Adversarial Prompt Tuning via Semantic ConceptsJan 1, 2026·Pedram MohajerAnsari,Zongxi Liu,Yi Zhu,Amir SalarpourMert D. Pesé· 0 min read PDF CiteTypeConference paperPublicationThe 6th Workshop of Adversarial Machine Learning on Computer Vision: Safety of Vision-Language AgentsLast updated on Jan 1, 2026 AuthorsMert D. PeséAssistant ProfessorMy research interests broadly lie in automotive security and privacy. ← FlexMap: Generalized HD Map Construction from Flexible Camera Configurations Jan 1, 2026NPNet: A Non-Parametric Network with Adaptive Gaussian-Fourier Positional Encoding for 3D Classification and Segmentation Jan 1, 2026 →
