Paper-Conference

Towards A Correct Usage of Cryptography in Semantic Watermarks for Diffusion Models

Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models

Selected paper for oral presentation

Are Semantic Watermarks for Diffusion Models Resilient to Layout Control?

The Impact of Uniform Inputs on Activation Sparsity and Energy-Latency Attacks in Computer Vision

Best Paper Award

AI-Generated Faces in the Real World: A Large-Scale Case Study of Twitter Profile Images

On the Detection of Image-Scaling Attacks in Machine Learning

No more Reviewer #2: Subverting Automatic Paper-Reviewer Assignment using Adversarial Learning

*=Shared first authorship

Misleading Deep-Fake Detection with GAN Fingerprints

Dos and Don'ts of Machine Learning in Computer Security

Distinguished Paper Award

Backdooring and Poisoning Neural Networks with Image-Scaling Attacks