52 citations · 189 across the 15 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.CR2026
Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction and Shuffling
Stefano Leggio, Giulio Rossolini, Alessandro Biondi
Vision Transformers (ViTs) are increasingly used in split-inference systems, where edge devices transmit intermediate token representations to a remote cloud. In this setting, toke…
cs.CV2026
PairedGTA: Generating Driving Datasets for Controlled Photometric Shift Analysis
Andrea Chianese, Giulio Rossolini, Alessandro Biondi +2
Evaluating the performance of visual perception systems for autonomous driving is essential to ensure reliable operation across diverse environmental scenarios. Ideally, a balanced…