The outstanding performance of deep neural networks has promoted deep learning applications in a broad set of domains. However, the potential risks caused by adversarial …
Abstract We propose the Square Attack, a score-based black-box l_2 l 2-and l_ ∞ l∞- adversarial attack that does not rely on local gradient information and thus is not affected by …
Deep Learning (DL) algorithms based on artificial neural networks have achieved remarkable success and are being extensively applied in a variety of application domains …
Current model extraction attacks assume that the adversary has access to a surrogate dataset with characteristics similar to the proprietary data used to train the victim model. This …
We study the problem of attacking a machine learning model in the hard-label black-box setting, where no model information is revealed except that the attacker can make queries to …
D Su, H Zhang, H Chen, J Yi… - Proceedings of the …, 2018 - openaccess.thecvf.com
The prediction accuracy has been the long-lasting and sole standard for comparing the performance of different image classification models, including the ImageNet competition …
GR Machado, E Silva, RR Goldschmidt - ACM Computing Surveys …, 2021 - dl.acm.org
Deep Learning algorithms have achieved state-of-the-art performance for Image Classification. For this reason, they have been used even in security-critical applications …
We consider the black-box adversarial setting, where the adversary has to generate adversarial perturbations without access to the target models to compute gradients. Previous …
Zeroth-order (ZO) optimization is a subset of gradient-free optimization that emerges in many signal processing and machine learning (ML) applications. It is used for solving optimization …