Fed-LSAE: Thwarting Poisoning Attacks against Federated Cyber Threat Detection System via Autoencoder-based Latent Space Inspection. (arXiv:2309.11053v1 [cs.CR])

The significant rise of security concerns in conventional centralized
learning has promoted federated learning (FL) adoption in building intelligent
applications without privacy breaches. In cybersecurity, the sensitive data
along with the contextual information and high-quality labeling in each
enterprise organization play an essential role in constructing high-performance
machine learning (ML) models for detecting cyber threats. Nonetheless, the
risks coming from poisoning internal adversaries against FL systems have raised
discussions about designing robust anti-poisoning frameworks. Whereas defensive
mechanisms in the past …

adoption applications attacks breaches cyber cybersecurity cyber threat cyber threat detection data detection enterprise fed federated learning high information inspection labeling organization play poisoning poisoning attacks privacy quality security security concerns sensitive sensitive data space system threat threat detection threat detection system