Boosting black-box attack to deep neural networks with conditional diffusion models

Boosting black-box attack to deep neural networks with conditional diffusion models

Existing black-box attacks have demonstrated promising potential in creating adversarial examples (AE) to deceive deep learning models. Most of these attacks need to handle a vast optimization space and require a large number of queries, hence exhibiting limited practical impacts in real-world scena...

Full description

Bibliographic Details
Main Authors: Liu, Renyang, Zhou, Wei, Zhang, tianwei, Chen, Kangiie, Zhao, Jun, Lam, Kwok-Yan
Other Authors: School of Computer Science and Engineering
Format: Journal Article
Language:English
Published: 2024
Subjects:
Computer and Information Science
Robustness
Perturbation methods
Online Access:https://hdl.handle.net/10356/179289

Similar Items

Similar Items