most citedOver-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing cs.AIShow all

2 papers · 1 filter

cs.AI2026

Latent-space Attacks for Refusal Evasion in Language Models

Giorgio Piras, Raffaele Mura, Fabio Brau +4

Safety-aligned language models are trained to refuse harmful requests, yet refusal behavior can be suppressed by steering their internal representations. Existing methods do so by…

cs.AI2025

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…