3 papers
cs.CV2026
A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Models
Mujtaba Hussain Mirza, Antonio D'Orazio, Odelia Melamed +1
Despite the rapid progress in multimodal models and Large Visual-Language Models (LVLM), they remain highly susceptible to adversarial perturbations, raising serious concerns about…
cs.CV2025
Implicit Inversion turns CLIP into a Decoder
Antonio D'Orazio, Maria Rosaria Briglia, Donato Crisostomi +3
CLIP is a discriminative model trained to align images and text in a shared embedding space. Due to its multimodal structure, it serves as the backbone of many generative pipelines…
cs.CV2024
Environment Maps Editing using Inverse Rendering and Adversarial Implicit Functions
Antonio D'Orazio, Davide Sforza, Fabio Pellacini +1
Editing High Dynamic Range (HDR) environment maps using an inverse differentiable rendering architecture is a complex inverse problem due to the sparsity of relevant pixels and the…