Deep neural networks have shown great potential in many practical applications, yet their knowledge is at the risk of being stolen via exposed services (\eg APIs). In contrast to the …
X Gong, Z Wang, S Li, Y Chen… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
With the development of deep learning, deep neural network (DNN)-based application have become an indispensable aspect of daily life. However, recent studies have shown that …
This paper aims to craft adversarial queries for image retrieval, which uses image features for similarity measurement. Many commonly used methods are developed in the context of …
L Meng, M Shao, F Wang, Y Qiao… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Convolutional neural networks (CNNs) are known to be vulnerable to adversarial examples even in black-box scenarios, posing a significant threat to their reliability and security. Most …
M Shao, L Meng, Y Qiao, L Zhang, W Zuo - arXiv preprint arXiv …, 2023 - arxiv.org
Since the training data for the target model in a data-free black-box attack is not available, most recent schemes utilize GANs to generate data for training substitute model. However …
M Duan, K Jiao, S Yu, Z Yang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
One area of current research on adversarial attacks is how to generate plausible adversarial examples when only a small number of datasets are available. Current adversarial attack …
M Zhang, Y Chen, H Li, C Qian, X Kuang - Neurocomputing, 2024 - Elsevier
Adversarial examples are known to have the property of transferability; as a result, deep neural networks can be compromised by transfer-based attacks in black-box scenarios …
Y Wei, Z Ma, Z Ma, Z Qin, Y Liu, B Xiao… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Recent substitute training methods have utilized the concept of Generative Adversarial Networks (GANs) to implement data-free black-box attacks. Specifically, in designing the …
R Li, J Yu, C Li, W Luo, Y Yuan, G Wang - arXiv preprint arXiv:2307.10997, 2023 - arxiv.org
Deep learning models are usually black boxes when deployed on machine learning platforms. Prior works have shown that the attributes ($ eg $, the number of convolutional …