14 papers
On the (In)Security of Loading Machine Learning Models
Gabriele Digregorio, Marco Di Gennaro, Stefano Zanero +2
The rise of model sharing through frameworks and dedicated hubs makes Machine Learning significantly more accessible. Despite its benefits, loading shared models exposes users to u…
LeakSealer: A Semisupervised Defense for LLMs Against Prompt Injection and Leakage Attacks
Francesco Panebianco, Stefano Bonfanti, Francesco Trovò +1
The generalization capabilities of Large Language Models (LLMs) have led to their widespread deployment across various applications. However, this increased adoption has introduced…
TimberStrike: Dataset Reconstruction Attack Revealing Privacy Leakage in Federated Tree-Based Systems
Marco Di Gennaro, Giovanni De Lucia, Stefano Longari +2
Federated Learning has emerged as a privacy-oriented alternative to centralized Machine Learning, enabling collaborative model training without direct data sharing. While extensive…
GOLIATH: A Decentralized Framework for Data Collection in Intelligent Transportation Systems
Davide Maffiola, Stefano Longari, Michele Carminati +2
Intelligent Transportation Systems (ITSs) technology has advanced during the past years, and it is now used for several applications that require vehicles to exchange real-time dat…
CyFence: Securing Cyber-Physical Controllers via Trusted Execution Environment
Stefano Longari, Alessandro Pozone, Jessica Leoni +4
In the last decades, Cyber-physical Systems (CPSs) have experienced a significant technological evolution and increased connectivity, at the cost of greater exposure to cyber-attac…
Assessing the Resilience of Automotive Intrusion Detection Systems to Adversarial Manipulation
Stefano Longari, Paolo Cerracchio, Michele Carminati +1
The security of modern vehicles has become increasingly important, with the controller area network (CAN) bus serving as a critical communication backbone for various Electronic Co…