.png){kind=icon}
Return
Memristive Crossbar Array-Based Adversarial Defense Using Compression
.png){kind=icon}
PRE
AI
DOI：10.1109/TETC.2023.3319659.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This article shows that Memristive Crossbar Array (MCA)-based neuromorphic architectures provide a robust defense against adversarial attacks due to the stochastic behavior of memristors. Furthermore, it shows that adversarial robustness can be further improved by compression-based preprocessing steps that can be implemented on MCAs. It also evaluates the effect of inter-chip process variations on adversarial robustness using the proposed MCA implementation and studies the effect of on-chip training. It shows that adversarial attacks do not uniformly affect the classification accuracy of different chips. Experimental evidence using a variety of datasets and attack models supports the impact of MCA-based neuromorphic architectures and compression-based preprocessing implemented using MCA on defending against adversarial attacks. It is also experimentally shown that the on-chip training results in high resiliency to adversarial attacks in all chips.
Keywords:
Robustness
Training
System-on-chip
Computer architecture
Memristors
Perturbation methods
Convolution
Adversarial attacks
adversarial defense
compressed sensing
compressed learning
MCA implementation
Journal
IF:
5.4
Papers:
1.1K
Citations:
3.4K
Organization
Cited Papers
.png){kind=icon}
ShareSaveCan microsomal RNA be a biomarker in pulmonary hypertension secondary to bronchopulmonary dysplasia?
PREAI
ShareSaveShareSaveShareSave
View more