On the Vulnerability of Hyperdimensional Computing-Based Classifiers to Adversarial Attacks | IBOOK.PUB

On the Vulnerability of Hyperdimensional Computing-Based Classifiers to Adversarial Attacks

Hyperdimensional computing (HDC) has been emerging as a brain-inspired in-memory computing architecture, exhibiting ultra energy efficiency, low latency and strong robustness against hardware-induced bit errors. Nonetheless, state-of-the-art designs for H

PDF / 27,845,979 Bytes
458 Pages / 439.37 x 666.142 pts Page_size
91 Downloads / 185 Views

Recommend Documents

On Security and Sparsity of Linear Classifiers for Adversarial Settings

152 82 52MB

Method of Comparison of Neural Network Resistance to Adversarial Attacks

179 31 45MB

Adversarial Example Attacks in the Physical World

177 38 65MB

Robust Tracking Against Adversarial Attacks

191 105 235MB

Universal Adversarial Perturbations and Image Spam Classifiers

192 7 23MB

Vulnerability of Network Coding Under Pollution Attacks

142 30 8MB

Assessing Adaptive Attacks Against Trained JavaScript Classifiers

172 98 34MB

Decision-based evasion attacks on tree ensemble classifiers

161 31 2MB

The Vulnerability of Multiplicative Noise Protection to Correlation-Attacks on Continuous Microdata

139 81 477KB

Emphasizing Similar Feature Representations to Defend Against Adversarial Attacks

185 113 126MB

APRICOT: A Dataset of Physical Adversarial Attacks on Object Detection

166 42 158MB

An Efficient Blurring-Reconstruction Model to Defend Against Adversarial Attacks

180 1 91MB