DNNGuard: An Elastic Heterogeneous DNN Accelerator Architecture against Adversarial Attacks

Xingbin Wang

Rui Hou

[0]

Boyan Zhao

Fengkai Yuan

Jun Zhang (张军)

[0]

Dan Meng (孟丹)

[0]

Xuehai Qian

ASPLOS '20: Architectural Support for Programming Languages and Operating Systems Lausanne Switzerland March, 2020, pp. 19-34, 2020.

Cited by: 0|Views173

Keywords:

DNN acceleratorHeterogeneous architectureAdversarial sampleDetection network

Weibo:

This paper proposes DNNGuard, an elastic heterogeneous Deep Neural Networks accelerator architecture that can efficiently orchestrate the simultaneous execution of original Deep Neural Networks networks and the detect algorithm or network that detects adversary sample attacks

Abstract:

Recent studies show that Deep Neural Networks (DNN) are vulnerable to adversarial samples that are generated by perturbing correctly classified inputs to cause the misclassification of DNN models. This can potentially lead to disastrous consequences, especially in security-sensitive applications such as unmanned vehicles, finance and heal...More

Code:

Data:

Full Text

View via Publisher