3 papers
cs.AI2026
Through the LENS: Local Geometric Decomposition of Vision-Language Model Representations
Shalom Kachko, Raz Lapid, Margarita Vald +2
Vision-language models (VLMs) process image patches and text tokens in a shared residual stream, but the local geometry through which the two modalities interact remains poorly und…
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.CV2024
Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectors
Raz Lapid, Almog Dubin, Moshe Sipper
This paper presents RADAR-Robust Adversarial Detection via Adversarial Retraining-an approach designed to enhance the robustness of adversarial detectors against adaptive attacks,…