Backdoor attacks are an important type of adversarial threat against deep neural network
classifiers, wherein test samples from one or more source classes will be (mis) classified to …

Recent studies revealed that using third-party models may lead to backdoor threats, where
adversaries can maliciously manipulate model predictions based on backdoors implanted …

Deep neural networks (DNNs) have been widely and successfully adopted and deployed in
various applications of speech recognition. Recently, a few works revealed that these …

Backdoor attack poses a significant security threat to Deep Learning applications. Existing
attacks are often not evasive to established backdoor detection techniques. This …

Backdoor attack is a common threat to deep neural networks. During testing, samples
embedded with a backdoor trigger will be misclassified as an adversarial target by a …

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

Backdoor attacks pose a significant security vulnerability for deep neural networks (DNNs),
enabling them to operate normally on clean inputs but manipulate predictions when specific …

Vision-Large-Language-models (VLMs) have great application prospects in autonomous
driving. Despite the ability of VLMs to comprehend and make decisions in complex …

Deep neural networks (DNNs) are susceptible to backdoor attacks, where adversaries
poison datasets with adversary-specified triggers to implant hidden backdoors, enabling …

Smart homes provide various services that serve people using AI (artificial intelligence)
models. In order to meet the changing demands, devices in smart homes independently …