Deep learning technology is increasingly being applied in safety-critical scenarios but has
recently been found to be susceptible to imperceptible adversarial perturbations. This raises …

In recent years, machine learning technology has made great improvements in social
networks applications such as social network recommendation systems, sentiment analysis …

Adversarial attacks seriously threaten the security of machine learning models. Thus,
detecting adversarial examples has become an important and interesting research topic …

Evading adversarial example detection defenses requires finding adversarial examples that
must simultaneously (a) be misclassified by the model and (b) be detected as non …

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

Deep neural networks (DNNs) are increasingly used in critical applications such as identity
authentication and autonomous driving, where robustness against adversarial attacks is …

While deep neural networks (DNNs) achieve impressive performance on environment
perception tasks, their sensitivity to adversarial perturbations limits their use in practical …

As an essential post-hoc explanatory method, counterfactual explanation enables people to
understand and react to machine learning models. Works on counterfactual explanation …

Deep neural network (DNN) accelerators received considerable attention in recent years
due to the potential to save energy compared to mainstream hardware. Low-voltage …

The vulnerability of deep neural networks against adversarial attacks, ie, imperceptible
adversarial perturbations can easily give rise to wrong predictions, poses a huge threat to …