On account of the extreme settings, stealing the black-box model without its training data is
difficult in practice. On this topic, along the lines of data diversity, this paper substantially …

Adversarial phenomenon has been widely observed in machine learning (ML) systems,
especially in those using deep neural networks, describing that ML systems may produce …

Black-box adversarial attacks have demonstrated strong potential to compromise machine
learning models by iteratively querying the target model or leveraging transferability from a …

Recent work has proposed stateful defense models (SDMs) as a compelling strategy to
defend against a black-box attacker who only has query access to the model, as is common …

Although fast adversarial training provides an efficient approach for building robust
networks, it may suffer from a serious problem known as catastrophic overfitting (CO), where …

Adversarial machine learning (AML) studies the adversarial phenomenon of machine
learning, which may make inconsistent or unexpected predictions with humans. Some …

Recently, the continuous evolution of deep learning has opened up promising avenues to
groundbreaking advancements in wireless sensing systems, which significantly enhance the …

The deep neural networks are known to be vulnerable to well-designed adversarial attacks.
The most successful defense technique based on adversarial training (AT) can achieve …

Adversarial examples are well-known tools to evaluate the vulnerability of deep neural
networks (DNNs). Although lots of adversarial attack algorithms have been developed, it is …

This paper proposes methods to upstage the best-known defences against query-based
black-box attacks. These benchmark defences incorporate gaussian noise into input data …