Deep learning systems are known to be vulnerable to adversarial examples. In particular,
query-based black-box attacks do not require knowledge of the deep learning model, but …

We consider adversarial examples for image classification in the black-box decision-based
setting. Here, an attacker cannot access confidence scores, but only the final label. Most …

Depending on how much information an adversary can access to, adversarial attacks can be
classified as white-box attack and black-box attack. For white-box attack, optimization-based …

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 …

Object detection has been widely used in many safety-critical tasks, such as autonomous
driving. However, its vulnerability to adversarial examples has not been sufficiently studied …

We study the most practical problem setup for evaluating adversarial robustness of a
machine learning system with limited access: the hard-label black-box attack setting for …

Compared to query-based black-box attacks, transfer-based black-box attacks do not
require any information of the attacked models, which ensures their secrecy. However, most …

We propose a versatile framework based on random search, Sparse-RS, for score-based
sparse targeted and untargeted attacks in the black-box setting. Sparse-RS does not rely on …

Generating adversarial examples in a black-box setting retains a significant challenge with
vast practical application prospects. In particular, existing black-box attacks suffer from the …

Existing black-box attacks on deep neural networks (DNNs) have largely focused on
transferability, where an adversarial instance generated for a locally trained model can …