3 papers
cs.CV2026
TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction
Nikos Athanasiou, Ilya A. Petrov, Angela Yao +7
Vision and vision-language models rely on high-level visual representations that are increasingly used across recognition, retrieval, and multimodal reasoning pipelines. However, r…
cs.CV2026
VGGT-
Jianyuan Wang, Minghao Chen, Shangzhan Zhang +7
Recent feed-forward reconstruction models, such as VGGT, have proven competitive with traditional optimization-based reconstructors while also providing geometry-aware features use…
cs.CV2020
Privacy-Preserving Image Features via Adversarial Affine Subspace Embeddings
Mihai Dusmanu, Johannes L. Schönberger, Sudipta N. Sinha +1
Many computer vision systems require users to upload image features to the cloud for processing and storage. These features can be exploited to recover sensitive information about…