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

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 …

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 …

The ever-evolving landscape of technology continually drives the demand for more robust
and secure systems. Intrusion Detection and Prevention Systems (IPS) play a pivotal role in …

Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks. In Natural
Language Processing (NLP), DNNs are often backdoored during the fine-tuning process of …

Since training a large-scale backdoored model from scratch requires a large training
dataset, several recent attacks have considered to inject backdoors into a trained clean …

This paper proposes a data-efficient detection method for deep neural networks against
backdoor attacks under a black-box scenario. The proposed approach is motivated by the …

A backdoor attack is a method that causes misrecognition in a deep neural network by
training it on additional data that have a specific trigger. The network will correctly recognize …

Deep neural networks provide good performance for image recognition, speech recognition,
text recognition, and pattern recognition. However, such networks are vulnerable to …

Despite the potential of federated learning, it is known to be vulnerable to backdoor attacks.
Many robust federated aggregation methods are proposed to reduce the potential backdoor …