Towards improving fast adversarial training in multi-exit network

Chen, Sihong; Shen, Haojing; Wang, Ran; Wang, Xizhao

doi:10.1016/j.neunet.2022.02.015

Neural Networks

2022

DOI: 10.1016/j.neunet.2022.02.015

|View full text |Cite

Towards improving fast adversarial training in multi-exit network

Sihong Chen

Haojing Shen

Ran Wang

et al.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2022

2024

Publication Types

Select...

Article5

Relationship

Self Cite0

Independent5

Authors

Journals

Cited by 5 publications

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Boosting adversarial robustness via feature refinement, suppression, and alignment

Wu,

Guo,

Chen

et al. 2024

Complex Intell. Syst.

View full text Add to dashboard Cite

Deep neural networks are vulnerable to adversarial attacks, bringing high risk to numerous security-critical applications. Existing adversarial defense algorithms primarily concentrate on optimizing adversarial training strategies to improve the robustness of neural networks, but ignore that the misguided decisions are essentially made by the activation values. Besides, such conventional strategies normally result in a great decline in clean accuracy. To address the above issues, we propose a novel RSA algorithm to counteract adversarial perturbations while maintaining clean accuracy. Specifically, RSA comprises three distinct modules: feature refinement, activation suppression, and alignment modules. First, the feature refinement module refines malicious activation values in the feature space. Subsequently, the feature activation suppression module mitigates redundant activation values induced by adversarial perturbations across both channel and spatial dimensions. Finally, to avoid an excessive performance drop on clean samples, RSA incorporates a consistency constraint and a knowledge distillation constraint for feature alignment. Extensive experiments on five public datasets and three backbone networks demonstrate that our proposed algorithm achieves consistently superior performance in both adversarial robustness and clean accuracy over the state-of-the-art.

show abstract

Boosting adversarial robustness via feature refinement, suppression, and alignment

Wu,

Guo,

Chen

et al. 2024

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

A novel compact design of convolutional layers with spatial transformation towards lower-rank representation for image classification

Liu

Han²,

Chen³

et al. 2022

Knowledge-Based Systems

View full text Add to dashboard Cite

Remix: Towards the transferability of adversarial examples

Zhao

Hao

et al. 2023

Neural Networks

View full text Add to dashboard Cite

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

hi@scite.ai

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Towards improving fast adversarial training in multi-exit network

Cited by 5 publications

References 4 publications

Boosting adversarial robustness via feature refinement, suppression, and alignment

Boosting adversarial robustness via feature refinement, suppression, and alignment

A novel compact design of convolutional layers with spatial transformation towards lower-rank representation for image classification

Remix: Towards the transferability of adversarial examples

Contact Info

Product

Resources

About