This work provides the community with a timely comprehensive review of backdoor attacks
and countermeasures on deep learning. According to the attacker's capability and affected …

With wide deployment of machine learning (ML)-based systems for a variety of applications
including medical, military, automotive, genomic, multimedia, and social networking, there is …

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 …

Together with impressive advances touching every aspect of our society, AI technology
based on Deep Neural Networks (DNN) is bringing increasing security concerns. While …

Backdoor attacks (BAs) are an emerging threat to deep neural network classifiers. A victim
classifier will predict to an attacker-desired target class whenever a test sample is …

Due to the greatly improved capabilities of devices, massive data, and increasing concern
about data privacy, Federated Learning (FL) has been increasingly considered for …

Although backdoor learning is an active research topic in the NLP domain, the literature
lacks studies that systematically categorize and summarize backdoor attacks and defenses …

With wide deployment of deep neural network (DNN) classifiers, there is great potential for
harm from adversarial learning attacks. Recently, a special type of data poisoning (DP) …

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 …

Backdoor attacks (BA) are an emerging threat to deep neural network classifiers. A classifier
being attacked will predict to the attacker's target class when a test sample from a source …