Adversarial attacks on Copyright Detection Systems

no code implementations • ICML 2020 • Parsa Saadatpanah, Ali Shafahi, Tom Goldstein

Our goal is to raise awareness of the threats posed by adversarial examples in this space, and to highlight the importance of hardening copyright detection systems to attacks.

Adversarially robust transfer learning

1 code implementation • ICLR 2020 • Ali Shafahi, Parsa Saadatpanah, Chen Zhu, Amin Ghiasi, Christoph Studer, David Jacobs, Tom Goldstein

By training classifiers on top of these feature extractors, we produce new models that inherit the robustness of their parent networks.

Transfer Learning