SCRAMBLE: A Secure and Configurable, Memristor-Based Neuromorphic Hardware Leveraging 3D Architecture

Nikhil Rangarajan; Satwik Patnaik; Mohammed Nabeel; Mohammed Ashraf; Shubham Rai; Gopal Raut; Heba Abunahla; Baker Mohammad; Santosh Kumar Vishvakarma; Akash Kumar; Johann Knechtel; Ozgur Sinanoglu

doi:10.1109/ISVLSI54635.2022.00067

SCRAMBLE: A Secure and Configurable, Memristor-Based Neuromorphic Hardware Leveraging 3D Architecture

Nikhil Rangarajan, Satwik Patnaik, Mohammed Nabeel, Mohammed Ashraf, Shubham Rai, Gopal Raut, Heba Abunahla, Baker Mohammad, Santosh Kumar Vishvakarma, Akash Kumar, Johann Knechtel, Ozgur Sinanoglu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this work we present SCRAMBLE, a configurable neuromorphic architecture that provides security against different threats by employing memristors for critical parts and functions. More specifically, we employ memristive memory cells - that are 3D stacked on top of the configurable neuromorphic hardware - to securely hold the weights as well as activation functions of any model processed on the generalized architecture. Thus, programmable memristive cells enable reconfiguration of the architecture to thwart both model stealing and hardware IP stealing attacks. We implement a proof-of-concept for the proposed architecture and analyze its security metrics. We also benchmark it against selected prior art for neuromorphic architectures to quantify the security-performance trade-offs.

Original language	English (US)
Title of host publication	Proceedings - 2022 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2022
Publisher	IEEE Computer Society
Pages	308-313
Number of pages	6
ISBN (Electronic)	9781665466059
DOIs	https://doi.org/10.1109/ISVLSI54635.2022.00067
State	Published - 2022
Event	2022 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2022 - Pafos, Cyprus Duration: Jul 4 2022 → Jul 6 2022

Publication series

Name	Proceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI
Volume	2022-July
ISSN (Print)	2159-3469
ISSN (Electronic)	2159-3477

Conference

Conference	2022 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2022
Country/Territory	Cyprus
City	Pafos
Period	7/4/22 → 7/6/22

ASJC Scopus subject areas

Hardware and Architecture
Control and Systems Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/ISVLSI54635.2022.00067

Cite this

Rangarajan, N., Patnaik, S., Nabeel, M., Ashraf, M., Rai, S., Raut, G., Abunahla, H., Mohammad, B., Vishvakarma, S. K., Kumar, A., Knechtel, J., & Sinanoglu, O. (2022). SCRAMBLE: A Secure and Configurable, Memristor-Based Neuromorphic Hardware Leveraging 3D Architecture. In Proceedings - 2022 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2022 (pp. 308-313). (Proceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI; Vol. 2022-July). IEEE Computer Society. https://doi.org/10.1109/ISVLSI54635.2022.00067

SCRAMBLE: A Secure and Configurable, Memristor-Based Neuromorphic Hardware Leveraging 3D Architecture. / Rangarajan, Nikhil; Patnaik, Satwik; Nabeel, Mohammed et al.
Proceedings - 2022 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2022. IEEE Computer Society, 2022. p. 308-313 (Proceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI; Vol. 2022-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Rangarajan, N, Patnaik, S, Nabeel, M, Ashraf, M, Rai, S, Raut, G, Abunahla, H, Mohammad, B, Vishvakarma, SK, Kumar, A, Knechtel, J & Sinanoglu, O 2022, SCRAMBLE: A Secure and Configurable, Memristor-Based Neuromorphic Hardware Leveraging 3D Architecture. in Proceedings - 2022 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2022. Proceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI, vol. 2022-July, IEEE Computer Society, pp. 308-313, 2022 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2022, Pafos, Cyprus, 7/4/22. https://doi.org/10.1109/ISVLSI54635.2022.00067

Rangarajan N, Patnaik S, Nabeel M, Ashraf M, Rai S, Raut G et al. SCRAMBLE: A Secure and Configurable, Memristor-Based Neuromorphic Hardware Leveraging 3D Architecture. In Proceedings - 2022 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2022. IEEE Computer Society. 2022. p. 308-313. (Proceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI). doi: 10.1109/ISVLSI54635.2022.00067

@inproceedings{bbef64c973474fcba14ae210c2a5f31b,

title = "SCRAMBLE: A Secure and Configurable, Memristor-Based Neuromorphic Hardware Leveraging 3D Architecture",

abstract = "In this work we present SCRAMBLE, a configurable neuromorphic architecture that provides security against different threats by employing memristors for critical parts and functions. More specifically, we employ memristive memory cells - that are 3D stacked on top of the configurable neuromorphic hardware - to securely hold the weights as well as activation functions of any model processed on the generalized architecture. Thus, programmable memristive cells enable reconfiguration of the architecture to thwart both model stealing and hardware IP stealing attacks. We implement a proof-of-concept for the proposed architecture and analyze its security metrics. We also benchmark it against selected prior art for neuromorphic architectures to quantify the security-performance trade-offs.",

author = "Nikhil Rangarajan and Satwik Patnaik and Mohammed Nabeel and Mohammed Ashraf and Shubham Rai and Gopal Raut and Heba Abunahla and Baker Mohammad and Vishvakarma, {Santosh Kumar} and Akash Kumar and Johann Knechtel and Ozgur Sinanoglu",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2022 ; Conference date: 04-07-2022 Through 06-07-2022",

year = "2022",

doi = "10.1109/ISVLSI54635.2022.00067",

language = "English (US)",

series = "Proceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI",

publisher = "IEEE Computer Society",

pages = "308--313",

booktitle = "Proceedings - 2022 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2022",

}

TY - GEN

T1 - SCRAMBLE

T2 - 2022 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2022

AU - Rangarajan, Nikhil

AU - Patnaik, Satwik

AU - Nabeel, Mohammed

AU - Ashraf, Mohammed

AU - Rai, Shubham

AU - Raut, Gopal

AU - Abunahla, Heba

AU - Mohammad, Baker

AU - Vishvakarma, Santosh Kumar

AU - Kumar, Akash

AU - Knechtel, Johann

AU - Sinanoglu, Ozgur

PY - 2022

Y1 - 2022

N2 - In this work we present SCRAMBLE, a configurable neuromorphic architecture that provides security against different threats by employing memristors for critical parts and functions. More specifically, we employ memristive memory cells - that are 3D stacked on top of the configurable neuromorphic hardware - to securely hold the weights as well as activation functions of any model processed on the generalized architecture. Thus, programmable memristive cells enable reconfiguration of the architecture to thwart both model stealing and hardware IP stealing attacks. We implement a proof-of-concept for the proposed architecture and analyze its security metrics. We also benchmark it against selected prior art for neuromorphic architectures to quantify the security-performance trade-offs.

AB - In this work we present SCRAMBLE, a configurable neuromorphic architecture that provides security against different threats by employing memristors for critical parts and functions. More specifically, we employ memristive memory cells - that are 3D stacked on top of the configurable neuromorphic hardware - to securely hold the weights as well as activation functions of any model processed on the generalized architecture. Thus, programmable memristive cells enable reconfiguration of the architecture to thwart both model stealing and hardware IP stealing attacks. We implement a proof-of-concept for the proposed architecture and analyze its security metrics. We also benchmark it against selected prior art for neuromorphic architectures to quantify the security-performance trade-offs.

UR - http://www.scopus.com/inward/record.url?scp=85140920230&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85140920230&partnerID=8YFLogxK

U2 - 10.1109/ISVLSI54635.2022.00067

DO - 10.1109/ISVLSI54635.2022.00067

M3 - Conference contribution

AN - SCOPUS:85140920230

T3 - Proceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI

SP - 308

EP - 313

BT - Proceedings - 2022 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2022

PB - IEEE Computer Society

Y2 - 4 July 2022 through 6 July 2022

ER -

SCRAMBLE: A Secure and Configurable, Memristor-Based Neuromorphic Hardware Leveraging 3D Architecture

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this