2 papers
cs.CV2026
SynthForensics: Benchmarking and Evaluating People-Centric Synthetic Video Deepfakes
Roberto Leotta, Salvatore Alfio Sambataro, Claudio Vittorio Ragaglia +5
Modern T2V/I2V generators synthesize people increasingly hard to distinguish from authentic footage, while current evaluation suites lag: legacy benchmarks target manipulation-base…
cs.CV2023
Not with my name! Inferring artists' names of input strings employed by Diffusion Models
Roberto Leotta, Oliver Giudice, Luca Guarnera +1
Diffusion Models (DM) are highly effective at generating realistic, high-quality images. However, these models lack creativity and merely compose outputs based on their training da…