WaSA: Wavelet Scattering Autoencoders for Unsupervised Offline Detection of Malicious Clients in Federated Learning

Name: WaSA: Wavelet Scattering Autoencoders for Unsupervised Offline Detection of Malicious Clients in Federated Learning
Uploaded: 2026-10-19T03:27:59.192227+00:00
Duration: 227 s
Description: WaSA proposes a fully unsupervised method to detect malicious clients in Federated Learning offline. It trains a denoising autoencoder on clean data prototypes to learn the structure of benign client representations. Clients are then scored based on their deviation from this learned benign manifold, allowing for detection of various attacks without needing prior knowledge of the threats.

WaSA proposes a fully unsupervised method to detect malicious clients in Federated Learning offline. It trains a denoising autoencoder on clean data prototypes to learn the structure of benign client representations. Clients are then scored based on their deviation from this learned benign manifold, allowing for detection of various attacks without needing prior knowledge of the threats.

Open the full episode