Voice Recognition Systems (VRSs) employ deep learning for speech recognition and
speaker recognition. They have been widely deployed in various real-world applications …

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries
embed a hidden backdoor trigger during the training process for malicious prediction …

Abstract Graph Neural Networks (GNNs) have emerged as a powerful tool for analyzing and
modeling graph-structured data. In recent years, GNNs have gained significant attention in …

Due to the increasing computational demand of Deep Neural Networks (DNNs), companies
and organizations have begun to outsource the training process. However, the externally …

In this paper, we study a defense against poisoned encoders in SSL called distillation, which
is a defense used in supervised learning originally. Distillation aims to distill knowledge from …

Backdoor attacks have severely threatened deep neural network (DNN) models in the past
several years. In backdoor attacks, the attackers try to plant hidden backdoors into DNN …

To mitigate recent insidious backdoor attacks on deep learning models, advances have
been made by the research community. Nonetheless, state-of-the-art defenses are either …

Self-supervised learning (SSL) is increasingly attractive for pre-training encoders without
requiring labeled data. Downstream tasks built on top of those pre-trained encoders can …

As a privacy-preserving distributed learning paradigm, federated learning (FL) has been
proven to be vulnerable to various attacks, among which backdoor attack is one of the …

Backdoor defense is crucial to ensure the safety and robustness of machine learning models
when under attack. However, most existing methods specialize in either the detection or …