Showing 2026Show all
3 papers · 1 filter
cs.CV2026
GDB-Reward: From Evaluation Metrics to Training Rewards for Graphic Design
Adrienne Deganutti, Purvanshi Mehta, Simon Hadfield +1
Text-to-image models excel at natural image synthesis but struggle with graphic design, where success depends on satisfying precise constraints on typography, layout, color, and vi…
cs.CR2026
SpooFL: Spoofing Federated Learning
Isaac Baglin, Xiatian Zhu, Simon Hadfield
Traditional defenses against Deep Leakage (DL) attacks in Federated Learning (FL) primarily focus on obfuscation, introducing noise, transformations or encryption to degrade an att…
cs.CV2026
Deep Leakage with Generative Flow Matching Denoiser
Isaac Baglin, Xiatian Zhu, Simon Hadfield
Federated Learning (FL) has emerged as a powerful paradigm for decentralized model training, yet it remains vulnerable to deep leakage (DL) attacks that reconstruct private client…