Rui Min

Privacy (1)

deep neural network (2) backdoor attack (2) backdoor defense (2) knowledge distillation (1) multimodal learning (1) content moderation (1) remote sensing (1) adversarial attack (1) multi-modal large language model (1) adversarial example (1) model purification (1) safety assessment (1) graph mining (1) trustworthy machine learning (1) teacher student learning (1) model watermarking (1) forensic investigation (1) model copy (1) geospatial reasoning (1) feature shift tuning (1)