4 papers
Antaeus: Hunting Repository-Level Logic Vulnerabilities via Context-Grounded LLM Reasoning
Michele Armillotta, Nicolò Romandini, Rebecca Montanari +1
LLM-based vulnerability detectors have shown promising results in identifying memory-safety bugs and vulnerability classes whose violations can often be expressed through establish…
SoK: Security and Privacy of AI Agents for Blockchain
Nicolò Romandini, Carlo Mazzocca, Kai Otsuki +1
Blockchain and smart contracts have garnered significant interest in recent years as the foundation of a decentralized, trustless digital ecosystem, thereby eliminating the need fo…
FedUP: Efficient Pruning-based Federated Unlearning for Model Poisoning Attacks
Nicolò Romandini, Cristian Borcea, Rebecca Montanari +1
Federated Learning (FL) can be vulnerable to attacks, such as model poisoning, where adversaries send malicious local weights to compromise the global model. Federated Unlearning (…
Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics
Nicolò Romandini, Alessio Mora, Carlo Mazzocca +2
Federated learning (FL) enables collaborative training of a machine learning (ML) model across multiple parties, facilitating the preservation of users' and institutions' privacy b…