Tag: machine learning security

Researchers at Soongsil University have developed a self-supervised, multi-view defense that detects label-flipping poisoning attacks in tabular machine learning by ...

Researchers have demonstrated a switchable backdoor attack that injects dual tokens through the layers of Vision Transformers, achieving up to ...

A systematic review of 93 studies reveals eight attack types and nine defence types across six categories of unsupervised machine ...

Researchers have built a federated learning system that combines CKKS homomorphic encryption with blockchain storage, cutting adversarial attack success from ...

Researchers have developed GRAB-FL, a graph-aware federated learning framework that uses graph neural networks to assign trust scores to client ...

A new survey in Artificial Intelligence Review unifies the four major attack vectors against voice authentication, finding that audio deepfakes ...

A new systematic survey maps the full landscape of privacy attacks on deep learning and finds that while differential privacy ...

Researchers have developed RecGP, a gradient penalty method that crafts transferable adversarial fake users by steering them toward flat regions ...