3 papers
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…
cs.CL2025
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…
cs.LG2024
Extracting Memorized Training Data via Decomposition
Ellen Su, Anu Vellore, Amy Chang +4
The widespread use of Large Language Models (LLMs) in society creates new information security challenges for developers, organizations, and end-users alike. LLMs are trained on la…