DeepFreeze : cold boot attacks and high fidelity model recovery on commercial EdgeML device

EdgeML accelerators like Intel Neural Compute Stick 2 (NCS) can enable efficient edge-based inference with complex pre-trained models. The models are loaded in the host (like Raspberry Pi) and then transferred to NCS for inference. In this paper, we demonstrate practical and low-cost cold boot based...

Full description

Saved in:
Bibliographic Details
Main Authors: Won, Yoo-Seung, Chatterjee, Soham, Jap, Dirmanto, Basu, Arindam, Bhasin, Shivam
Other Authors: School of Electrical and Electronic Engineering
Format: Conference or Workshop Item
Language:English
Published: 2022
Subjects:
Online Access:https://hdl.handle.net/10356/156094
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:EdgeML accelerators like Intel Neural Compute Stick 2 (NCS) can enable efficient edge-based inference with complex pre-trained models. The models are loaded in the host (like Raspberry Pi) and then transferred to NCS for inference. In this paper, we demonstrate practical and low-cost cold boot based model recovery attacks on NCS to recover the model architecture and weights, loaded from the Raspberry Pi. The architecture is recovered with 100% success and weights with an error rate of 0.04%. The recovered model reports maximum accuracy loss of 0.5% as compared to original model and allows high fidelity transfer of adversarial examples. We further extend our study to other cold boot attack setups reported in the literature with higher error rates leading to accuracy loss as high as 70%. We then propose a methodology based on knowledge distillation to correct the erroneous weights in recovered model, even without access to original training data. The proposed attack remains unaffected by the model encryption features of the OpenVINO and NCS framework.