2 papers
cs.LG2026
Gradient Concentration, Not Weight Saliency, Explains Representation-Level Class Unlearning
Billel Habbati, Alessio Merlo, Luca Verderame +1
Machine unlearning aims to remove the influence of specific training data while preserving model utility. Many state-of-the-art approaches pursue this goal by restricting the forge…
cs.CR2026
PolicyGapper: Automated Detection of Inconsistencies Between Google Play Data Safety Sections and Privacy Policies Using LLMs
Luca Ferrari, Billel Habbati, Meriem Guerar +2
Mobile application developers are required to disclose how they collect, use, and share user data in compliance with privacy regulations. To support transparency, major app marketp…