5 papers
Test-Time Attention Purification for Backdoored Large Vision Language Models
Zhifang Zhang, Bojun Yang, Shuo He +5
Despite the strong multimodal performance, large vision-language models (LVLMs) are vulnerable during fine-tuning to backdoor attacks, where adversaries insert trigger-embedded sam…
Unlearning Evaluation through Subset Statistical Independence
Chenhao Zhang, Muxing Li, Feng Liu +2
Evaluating machine unlearning remains challenging, as existing methods typically require retraining reference models or performing membership inference attacks, both of which rely…
Machine Unlearning for Streaming Forgetting
Shaofei Shen, Chenhao Zhang, Yawen Zhao +3
Machine unlearning aims to remove knowledge of the specific training data in a well-trained model. Currently, machine unlearning methods typically handle all forgetting data in a s…
We Care Each Pixel: Calibrating on Medical Segmentation Model
Wenhao Liang, Wei Zhang, Lin Yue +3
Medical image segmentation is fundamental for computer-aided diagnostics, providing accurate delineation of anatomical structures and pathological regions. While common metrics suc…
Toward Efficient Data-Free Unlearning
Chenhao Zhang, Shaofei Shen, Weitong Chen +1
Machine unlearning without access to real data distribution is challenging. The existing method based on data-free distillation achieved unlearning by filtering out synthetic sampl…