15 citations · 48 across the 19 of their papers we have counts for
Showing 2025 · cs.CVShow all
2 papers · 2 filters
cs.CV2025
Backdoors in Conditional Diffusion: Threats to Responsible Synthetic Data Pipelines
Raz Lapid, Almog Dubin
Text-to-image diffusion models achieve high-fidelity image generation from natural language prompts. ControlNets extend these models by enabling conditioning on structural inputs (…
cs.CV2025
Pulling Back the Curtain: Unsupervised Adversarial Detection via Contrastive Auxiliary Networks
Eylon Mizrahi, Raz Lapid, Moshe Sipper
Deep learning models are widely employed in safety-critical applications yet remain susceptible to adversarial attacks -- imperceptible perturbations that can significantly degrade…