A measure of robustness against naturally occurring distortions is key to safety, success, and
trustworthiness of machine learning models on deployment. We propose an adversarial …

The score-based query attacks (SQAs) pose practical threats to deep neural networks by
crafting adversarial perturbations within dozens of queries, only using the model's output …

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 …

We propose a Reinforcement Learning (RL) based adversarial Black-box attack (RLAB) that
aims at adding minimum distortion to the input iteratively to deceive image classification …

Numerous works study black-box attacks on image classifiers, where adversaries generate
adversarial examples against unknown target models without having access to their internal …

The wide application of deep neural networks (DNNs) demands an increasing amount of
attention to their real-world robustness, ie, whether a DNN resists black-box adversarial …