3 papers
cs.CR2024
DiffBreak: Is Diffusion-Based Purification Robust?
Andre Kassis, Urs Hengartner, Yaoliang Yu
Diffusion-based purification (DBP) has become a cornerstone defense against adversarial examples (AEs), regarded as robust due to its use of diffusion models (DMs) that project AEs…
cs.CR2024
UnMarker: A Universal Attack on Defensive Image Watermarking
Andre Kassis, Urs Hengartner
Reports regarding the misuse of Generative AI (GenAI) to create deepfakes are frequent. Defensive watermarking enables GenAI providers to hide fingerprints in their images and use…
cs.CR2023
On the Feasibility of Fingerprinting Collaborative Robot Network Traffic
Cheng Tang, Diogo Barradas, Urs Hengartner +1
This study examines privacy risks in collaborative robotics, focusing on the potential for traffic analysis in encrypted robot communications. While previous research has explored…