3 papers
cs.AI2026
LeakBoost: Perceptual-Loss-Based Membership Inference Attack
Amit Kravchik Taub, Fred M. Grabovski, Guy Amit +1
Membership inference attacks (MIAs) aim to determine whether a sample was part of a model's training set, posing serious privacy risks for modern machine-learning systems. Existing…
cs.CR2025
Memory Backdoor Attacks on Neural Networks
Eden Luzon, Guy Amit, Roy Weiss +3
Neural networks are often trained on proprietary datasets, making them attractive attack targets. We present a novel dataset extraction method leveraging an innovative training tim…
eess.IV2024
Back-in-Time Diffusion: Unsupervised Detection of Medical Deepfakes
Fred Grabovski, Lior Yasur, Guy Amit +1
Recent progress in generative models has made it easier for a wide audience to edit and create image content, raising concerns about the proliferation of deepfakes, especially in h…