English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

With deep learning deployed in many security-sensitive areas, machinelearning security is becoming progressively important. Recent studiesdemonstrate attackers can exploit system-level techniques exploiting theRowHammer vulnerability of DRAM to deterministically and precisely flip bits inDeep Neural Networks (DNN) model weights to affect inference accuracy. Theexisting defense mechanisms are software-based, such as weight reconstructionrequiring expensive training overhead or performance degradation. On the otherhand, generic hardware-based victim-/aggressor-focused mechanisms imposeexpensive hardware overheads and preserve the spatial connection between victimand aggressor rows. In this paper, we present the first DRAM-basedvictim-focused defense mechanism tailored for quantized DNNs, namedDNN-Defender that leverages the potential of in-DRAM swapping to withstand thetargeted bit-flip attacks. Our results indicate that DNN-Defender can deliver ahigh level of protection downgrading the performance of targeted RowHammerattacks to a random attack level. In addition, the proposed defense has noaccuracy drop on CIFAR-10 and ImageNet datasets without requiring any softwaretraining or incurring additional hardware overhead.

DNN-Defender: An in-DRAM Deep Neural Network Defense Mechanism for Adversarial Weight Attack