Search Results for author:
Found 5 papers, 1 papers with code
Starlit: Privacy-Preserving Federated Learning to Enhance Financial Fraud Detection
Federated Learning (FL) is a data-minimization approach enabling collaborative model training across diverse clients with local data, avoiding direct data exchange.
BadVFL: Backdoor Attacks in Vertical Federated Learning
In VFL, the participants share the same set of training instances but only host a different and non-overlapping subset of the whole feature space.
Cerberus: Exploring Federated Prediction of Security Events
Modern defenses against cyberattacks increasingly rely on proactive approaches, e. g., to predict the adversary's next actions based on past events.
Bayesian Estimation of Differential Privacy
Our Bayesian method exploits the hypothesis testing interpretation of differential privacy to obtain a posterior for $\varepsilon$ (not just a confidence interval) from the joint posterior of the false positive and false negative rates of membership inference attacks.
Local and Central Differential Privacy for Robustness and Privacy in Federated Learning
This paper investigates whether and to what extent one can use differential Privacy (DP) to protect both privacy and robustness in FL.
