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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

EdgeML accelerators like Intel Neural Compute Stick 2 (NCS) can enableefficient edge-based inference with complex pre-trained models. The models areloaded in the host (like Raspberry Pi) and then transferred to NCS forinference. In this paper, we demonstrate practical and low-cost cold boot basedmodel recovery attacks on NCS to recover the model architecture and weights,loaded from the Raspberry Pi. The architecture is recovered with 100% successand weights with an error rate of 0.04%. The recovered model reports maximumaccuracy loss of 0.5% as compared to original model and allows high fidelitytransfer of adversarial examples. We further extend our study to other coldboot attack setups reported in the literature with higher error rates leadingto accuracy loss as high as 70%. We then propose a methodology based onknowledge distillation to correct the erroneous weights in recovered model,even without access to original training data. The proposed attack remainsunaffected by the model encryption features of the OpenVINO and NCS framework.

DeepFreeze: Cold Boot Attacks and High Fidelity Model Recovery on Commercial EdgeML Device