Ilya A. Petrov

TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction

Nikos Athanasiou, Ilya A. Petrov, Angela Yao, Shugao Ma, Eric Sauser, Edoardo Remelli, et al.

Vision and vision-language models rely on high-level visual representations that are increasingly used across recognition, retrieval, and multimodal reasoning pipelines. However, recent advances in generative modeling have shown that such features can often be inverted, enabling…Read more