5 citations · 5 across the 2 of their papers we have counts for
2 papers
cs.CR2025
Attacking Attention of Foundation Models Disrupts Downstream Tasks
Hondamunige Prasanna Silva, Federico Becattini, Lorenzo Seidenari
Foundation models represent the most prominent and recent paradigm shift in artificial intelligence. Foundation models are large models, trained on broad data that deliver high acc…
cs.LG2023★ 5 cited
DiffDefense: Defending against Adversarial Attacks via Diffusion Models
Hondamunige Prasanna Silva, Lorenzo Seidenari, Alberto Del Bimbo
This paper presents a novel reconstruction method that leverages Diffusion Models to protect machine learning classifiers against adversarial attacks, all without requiring any mod…