Saliency-based representation visualization (SRV)($ eg $, Grad-CAM) is one of the most
classical and widely adopted explainable artificial intelligence (XAI) methods for its simplicity …

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where a backdoored
model behaves normally with clean inputs but exhibits attacker-specified behaviors upon the …

Abstract The use of Controller Area Network in advanced automobiles as a communication
technology is becoming more common. However, there is a lack of adequate privacy …

Backdoor attacks in the traditional graph neural networks (GNNs) field are easily detectable
due to the dilemma of confusing labels. To explore the backdoor vulnerability of GNNs and …

Backdoor attacks aim to inject backdoors to victim machine learning models during training
time, such that the backdoored model maintains the prediction power of the original model …

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries can
maliciously trigger model misclassifications by implanting a hidden backdoor during model …

Recently, with the development and widespread application of deep neural networks
(DNNs), backdoor attacks have posed new security threats to the training process of DNNs …

Backdoor attacks can exploit vulnerabilities in the training process of Deep Neural Networks
(DNNs), introducing hidden malicious functionality that can be activated by a specific input …

Backdoor attacks have been widely studied for image classification tasks, but rarely
investigated for video recognition tasks. In this paper, we explore the possibility of physically …

Object detectors are vulnerable to backdoor attacks. In contrast to classifiers, detectors
possess unique characteristics, architecturally and in task execution; often operating in …