76 citations · 100 across the 15 of their papers we have counts for
5 papers · 1 filter
DROP: Poison Dilution via Knowledge Distillation for Federated Learning
Georgios Syros, Anshuman Suri, Farinaz Koushanfar +2
Federated Learning is vulnerable to adversarial manipulation, where malicious clients can inject poisoned updates to influence the global model's behavior. While existing defense m…
SureFED: Robust Federated Learning via Uncertainty-Aware Inward and Outward Inspection
Nasimeh Heydaribeni, Ruisi Zhang, Tara Javidi +2
In this work, we introduce SureFED, a novel framework for byzantine robust federated learning. Unlike many existing defense methods that rely on statistically robust quantities, ma…
Backdoor Attacks in Peer-to-Peer Federated Learning
Georgios Syros, Gokberk Yar, Simona Boboila +2
Most machine learning applications rely on centralized learning processes, opening up the risk of exposure of their training datasets. While federated learning (FL) mitigates to so…
Are Self-Driving Cars Secure? Evasion Attacks against Deep Neural Networks for Steering Angle Prediction
Alesia Chernikova, Alina Oprea, Cristina Nita-Rotaru +1
Deep Neural Networks (DNNs) have tremendous potential in advancing the vision for self-driving cars. However, the security of DNN models in this context leads to major safety impli…
Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks
Ambra Demontis, Marco Melis, Maura Pintor +5
Transferability captures the ability of an attack against a machine-learning model to be effective against a different, potentially unknown, model. Empirical evidence for transfera…