6 papers
Exploring and Bridging Knowledge Holes in Unlearned Multimodal Large Language Models
Junxiang You, Junkai Chen, Yuhao He +3
Machine unlearning offers a promising approach to remove unsafe content from Multimodal Large Language Models (MLLMs), yet ensuring the precision of unlearning remains a persistent…
Toward Fine-Grained Forgetting:Attribute Unlearning for Multimodal Large Language Models
Junkai Lin, Junkai Chen, Siqi Hou +5
Multimodal large language models (MLLMs) exhibit strong vision--language capabilities but may also memorize and disclose sensitive information. Machine unlearning seeks to remove d…
Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning
Junkai Chen, Yuhao He, Junxiang You +3
Multimodal Large Language Models (MLLMs) have achieved remarkable progress on vision-language tasks, but they may also memorize and expose sensitive or restricted knowledge, raisin…
RABC-Net: Reliability-Aware Annotation-Free Skin Lesion Segmentation for Low-Resource Dermoscopy
Yujie Yao, Yuhaohang He, Junjie Huang +6
Pixel-level annotation is costly in low-resource dermoscopy. We present RABC-Net, a reliability-aware annotation-free segmentation system that combines pseudo-label reliability lea…
Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization
Yuhao He, Jinyu Tian, Xianwei Zheng +3
Recent studies have shown that deep learning models are very vulnerable to poisoning attacks. Many defense methods have been proposed to address this issue. However, traditional po…
Structure Disruption: Subverting Malicious Diffusion-Based Inpainting via Self-Attention Query Perturbation
Yuhao He, Jinyu Tian, Haiwei Wu +1
The rapid advancement of diffusion models has enhanced their image inpainting and editing capabilities but also introduced significant societal risks. Adversaries can exploit user…