2 papers
cs.AI2026
Does Forgetting Transfer Across Modalities? A Real-World Benchmark for Cross-Modal Knowledge Unlearning Evaluation
Chunlin Liu, Junnian Chen, Haitong Jiang +7
Vision-Language Models (VLMs), like Large Language Models (LLMs), may memorize sensitive, copyrighted, or harmful knowledge from their pretraining corpora. Removing such knowledge…
cs.CV2025
TTP: Test-Time Padding for Adversarial Detection and Robust Adaptation on Vision-Language Models
Zhiwei Li, Yitian Pang, Weining Wang +2
Vision-Language Models (VLMs), such as CLIP, have achieved impressive zero-shot recognition performance but remain highly susceptible to adversarial perturbations, posing significa…