Pelta: Shielding Transformers to Mitigate Evasion Attacks in Federated Learning

no code implementations • 8 Aug 2023 • Simon Queyrut, Yérom-David Bromberg, Valerio Schiavoni

The main premise of federated learning is that machine learning model updates are computed locally, in particular to preserve user data privacy, as those never leave the perimeter of their device.

Adversarial Attack Federated Learning

Spores: Stateless Predictive Onion Routing for E-Squads

no code implementations • 2 Jul 2020 • Daniel Bosk, Yérom-David Bromberg, Sonja Buchegger, Adrien Luxey, François Taïani

Mass surveillance of the population by state agencies and corporate parties is now a well-known fact.