14 papers
Adversarial Decoys: Misdirecting Attention-Based Defenses in ViT
Giulia Marchiori Pietrosanti, Giulio Rossolini, Giorgio Buttazzo
Vision Transformers (ViTs) remain vulnerable to localized adversarial attacks, e.g., adversarial patches, while recent test-time defenses mitigate them by suppressing image tokens…
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…
Learning Robustness at Test-Time from a Non-Robust Teacher
Stefano Bianchettin, Giulio Rossolini, Giorgio Buttazzo
Nowadays, pretrained models are increasingly used as general-purpose backbones and adapted at test-time to downstream environments where target data are scarce and unlabeled. While…
How Worst-Case Are Adversarial Attacks? Linking Adversarial and Perturbation Robustness
Giulio Rossolini
Adversarial attacks are widely used to identify model vulnerabilities; however, their validity as proxies for robustness to random perturbations remains debated. We ask whether an…
On the Hidden Objective Biases of Group-based Reinforcement Learning
Aleksandar Fontana, Marco Simoni, Giulio Rossolini +2
Group-based reinforcement learning methods, like Group Relative Policy Optimization (GRPO), are widely used nowadays to post-train large language models. Despite their empirical su…
GTPO: Stabilizing Group Relative Policy Optimization via Gradient and Entropy Control
Marco Simoni, Aleksandar Fontana, Giulio Rossolini +2
Group Relative Policy Optimization (GRPO) is a promising policy-based approach for Large Language Model alignment, yet its performance is often limited by training instability and…