Privacy-Shielded Image Compression: Defending Against Exploitation from Vision-Language Pretrained Models

Xuelin Shen; Jiayin Xu; Kangsheng Yin; Wenhan Yang

2025 ICML ICML 2025

Privacy-Shielded Image Compression: Defending Against Exploitation from Vision-Language Pretrained Models

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Xuelin Shen, Jiayin Xu, Kangsheng Yin, Wenhan Yang

Topics

Artificial Intelligence > Core AI > Multimodal Learning Machine Learning > Application Areas > Domain Adaptation Deep Learning > Models > Generative Models

Keywords

semantic information learned image compression vision-language pretrained model conditional latent trigger generation privacy-shielded image compression uncertainty-aware encryption-oriented optimization

Download PDF