1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Learning To Characterize Adversarial Subspaces

Learning To Characterize Adversarial Subspaces

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

Deep Neural Networks (DNNs) are known to be vulnerable to the maliciously generated adversarial examples. To detect these adversarial examples, previous methods use artificially designed metrics to characterize the properties of adversarial subspaces wher

• IEEE MemberUS $11.00
• Society MemberUS $0.00
• IEEE Student MemberUS $11.00
• Non-IEEE MemberUS $15.00

Purchase

Videos in this product

Learning To Characterize Adversarial Subspaces

00:13:07

0 views

Deep Neural Networks (DNNs) are known to be vulnerable to the maliciously generated adversarial examples. To detect these adversarial examples, previous methods use artificially designed metrics to characterize the properties of adversarial subspaces wher