10 citations · 20 across the 14 of their papers we have counts for
5 papers · 1 filter
SOM Directions are Better than One: Multi-Directional Refusal Suppression in Language Models
Giorgio Piras, Raffaele Mura, Fabio Brau +3
Refusal refers to the functional behavior enabling safety-aligned language models to reject harmful or unethical prompts. Following the growing scientific interest in mechanistic i…
LatentBreak: Jailbreaking Large Language Models through Latent Space Feedback
Raffaele Mura, Giorgio Piras, Kamilė Lukošiūtė +3
Jailbreaks are adversarial attacks designed to bypass the built-in safety mechanisms of large language models. Automated jailbreaks typically optimize an adversarial suffix or adap…
S2AP: Score-space Sharpness Minimization for Adversarial Pruning
Giorgio Piras, Qi Zhao, Fabio Brau +3
Adversarial pruning methods have emerged as a powerful tool for compressing neural networks while preserving robustness against adversarial attacks. These methods typically follow…
Evaluating Line-level Localization Ability of Learning-based Code Vulnerability Detection Models
Marco Pintore, Giorgio Piras, Angelo Sotgiu +2
To address the extremely concerning problem of software vulnerability, system security is often entrusted to Machine Learning (ML) algorithms. Despite their now established detecti…
Regression-aware Continual Learning for Android Malware Detection
Daniele Ghiani, Daniele Angioni, Giorgio Piras +6
Malware evolves rapidly, forcing machine learning-based detectors to be continuously updated. With antivirus vendors processing hundreds of thousands of new samples daily, datasets…