Guarder: A Stable and Lightweight Reconfigurable RRAM-based PIM Accelerator for DNN IP Protection

Deploying deep neural networks (DNNs) on conventional digital edge devices faces significant challenges due to high energy consumption. A promising solution is the processing-inmemory (PIM) architecture with resistive random-access memory (RRAM), but RRAM-based systems suffer from imprecise weights...

Full description

Saved in:
Bibliographic Details
Published in:2025 62nd ACM/IEEE Design Automation Conference (DAC) pp. 1 - 7
Main Authors: Lin, Ning, Li, Yi, Li, Jiankun, Yang, Jichang, He, Yangu, Luo, Yukui, Shang, Dashan, Chen, Xiaoming, Qi, Xiaojuan, Wang, Zhongrui
Format: Conference Proceeding
Language:English
Published: IEEE 22.06.2025
Subjects:
Artificial neural networks
Contrastive training
Cryptography
Energy consumption
Hardware
IP Protection
PIM
Programming
Protection
Reconfigration
Robustness
Software
Software reliability
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Deploying deep neural networks (DNNs) on conventional digital edge devices faces significant challenges due to high energy consumption. A promising solution is the processing-inmemory (PIM) architecture with resistive random-access memory (RRAM), but RRAM-based systems suffer from imprecise weights due to programming stochasticity and cannot effectively utilize conventional weight encryption/decryption intellectual property (IP) protection schemes. To address these issues, we propose a novel software-hardware co-design Guarder. On the hardware side, we introduce 3T2R cells to achieve reliable multiply-accumulate (MAC) operations and use reconfigurable inverter operating voltages to encode keys for encrypting DNNs on RRAM. On the software side, we implement a contrastive training method that ensures high model accuracy on authorized chips while degrading performance on unauthorized ones. This approach protects DNN IP with minimal hardware overhead while significantly mitigating the effects of RRAM programming stochasticity. Extensive experiments on tasks such as image classification (using MLP, ResNet, and ViT), segmentation (using SegFormer), and image generation (using DiT) validate the effectiveness of our method. The proposed contrastive training ensures negligible performance degradation on authorized chips, while performance on unauthorized chips drops to random guessing or generation. Compared to traditional RRAM accelerators, the 3T2R-based accelerator achieves a 1.41 \times reduction in area overhead and a 2.28 \times reduction in energy consumption.
AbstractList Deploying deep neural networks (DNNs) on conventional digital edge devices faces significant challenges due to high energy consumption. A promising solution is the processing-inmemory (PIM) architecture with resistive random-access memory (RRAM), but RRAM-based systems suffer from imprecise weights due to programming stochasticity and cannot effectively utilize conventional weight encryption/decryption intellectual property (IP) protection schemes. To address these issues, we propose a novel software-hardware co-design Guarder. On the hardware side, we introduce 3T2R cells to achieve reliable multiply-accumulate (MAC) operations and use reconfigurable inverter operating voltages to encode keys for encrypting DNNs on RRAM. On the software side, we implement a contrastive training method that ensures high model accuracy on authorized chips while degrading performance on unauthorized ones. This approach protects DNN IP with minimal hardware overhead while significantly mitigating the effects of RRAM programming stochasticity. Extensive experiments on tasks such as image classification (using MLP, ResNet, and ViT), segmentation (using SegFormer), and image generation (using DiT) validate the effectiveness of our method. The proposed contrastive training ensures negligible performance degradation on authorized chips, while performance on unauthorized chips drops to random guessing or generation. Compared to traditional RRAM accelerators, the 3T2R-based accelerator achieves a 1.41 \times reduction in area overhead and a 2.28 \times reduction in energy consumption.
Author He, Yangu
Yang, Jichang
Li, Jiankun
Wang, Zhongrui
Luo, Yukui
Qi, Xiaojuan
Li, Yi
Lin, Ning
Shang, Dashan
Chen, Xiaoming
Author_xml – sequence: 1
  givenname: Ning
  surname: Lin
  fullname: Lin, Ning
  organization: The University of Hong Kong,Department of Electrical and Electronic Engineering,Hong Kong,China
– sequence: 2
  givenname: Yi
  surname: Li
  fullname: Li, Yi
  organization: The University of Hong Kong,Department of Electrical and Electronic Engineering,Hong Kong,China
– sequence: 3
  givenname: Jiankun
  surname: Li
  fullname: Li, Jiankun
  organization: The University of Hong Kong,Department of Electrical and Electronic Engineering,Hong Kong,China
– sequence: 4
  givenname: Jichang
  surname: Yang
  fullname: Yang, Jichang
  organization: The University of Hong Kong,Department of Electrical and Electronic Engineering,Hong Kong,China
– sequence: 5
  givenname: Yangu
  surname: He
  fullname: He, Yangu
  organization: The University of Hong Kong,Department of Electrical and Electronic Engineering,Hong Kong,China
– sequence: 6
  givenname: Yukui
  surname: Luo
  fullname: Luo, Yukui
  organization: Binghamton University, State University of New York,Binghamton,NY,USA
– sequence: 7
  givenname: Dashan
  surname: Shang
  fullname: Shang, Dashan
  organization: Institute of Microelectronics of the Chinese Academy of Sciences (CAS),State Key Lab of Fabrication Technologies for Integrated Circuits and Key Laboratory of Microelectronic Devices and Integrated Technology,Beijing,China
– sequence: 8
  givenname: Xiaoming
  surname: Chen
  fullname: Chen, Xiaoming
  email: chenxiaoming@ict.ac.cn
  organization: Institute of Computing Technology of CAS,Beijing,China
– sequence: 9
  givenname: Xiaojuan
  surname: Qi
  fullname: Qi, Xiaojuan
  email: xjqi@eee.hku.hk
  organization: The University of Hong Kong,Department of Electrical and Electronic Engineering,Hong Kong,China
– sequence: 10
  givenname: Zhongrui
  surname: Wang
  fullname: Wang, Zhongrui
  email: wangzr@sustech.edu.cn
  organization: Southern University of Science and Technology,School of Microelectronics,Shenzhen,China
BookMark eNo1T11Lw0AQPEEftPYfiNwfSL2vJHe-hVZrIK0h6nPZu-zVQEzkekX898Yv2JldZpiBvSCnwzggIdecLThn5mZVLDOplVkIJtJJ4lJOc0LmJjd6ulMmmdLnBNZHCC2GW1rQpwi2RwpDS6tu_xo_8Jtpg24cfLc_hh-7aYpNYuGALa3LDS2cwx4DxDFQP2G13dKypnUYI7rYjcMlOfPQH3D-t2fk5f7uefmQVI_rcllUCfDcxIRbI3ObecttKzlojYipYimkQvhMKIfoPXepUq0SBkSmQACHVjvJc5tzOSNXv73dlNy9h-4Nwufu_3P5BW58Ufg
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/DAC63849.2025.11133133
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library (IEL) (UW System Shared)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library (IEL) (UW System Shared)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331503048
EndPage 7
ExternalDocumentID 11133133
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  funderid: 10.13039/501100001809
GroupedDBID 6IE
6IH
CBEJK
RIE
RIO
ID FETCH-LOGICAL-a179t-1b937b6fb1bd31a88eee5405a522f624ceeff1c544d429a264a2a1ad8c317b713
IEDL.DBID RIE
IngestDate Wed Oct 01 07:05:15 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a179t-1b937b6fb1bd31a88eee5405a522f624ceeff1c544d429a264a2a1ad8c317b713
PageCount 7
ParticipantIDs ieee_primary_11133133
PublicationCentury 2000
PublicationDate 2025-June-22
PublicationDateYYYYMMDD 2025-06-22
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-June-22
  day: 22
PublicationDecade 2020
PublicationTitle 2025 62nd ACM/IEEE Design Automation Conference (DAC)
PublicationTitleAbbrev DAC
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
Score 2.295285
Snippet Deploying deep neural networks (DNNs) on conventional digital edge devices faces significant challenges due to high energy consumption. A promising solution is...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Artificial neural networks
Contrastive training
Cryptography
Energy consumption
Hardware
IP Protection
PIM
Programming
Protection
Reconfigration
Robustness
Software
Software reliability
Training
Title Guarder: A Stable and Lightweight Reconfigurable RRAM-based PIM Accelerator for DNN IP Protection
URI https://ieeexplore.ieee.org/document/11133133
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFA9uePCkYsVvcvCarc2yNPVWNocDV8pQ2G3kUwbSSe303_cl6xQPHoQeQhOaj9fy-73k_foQumVZqjSlhihqB4RxFhOpBJRibqwExFBum2wiLQqxWGRlK1YPWhhrbQg-sz1fDGf5Zq03fqus79OiD-DqoE6a8q1Yq1X9JnHWH-cjeJuYl5_QYW_X-FfalIAak8N_9neEoh_9HS6_keUY7dnqBMlgTVvf4RwDRVSvFsvK4EfvXX-GDU7sfcnKrV42daiez_MZ8TBlcDmd4VxrwJhwrI6BquJxUeBp6TtqQjxWFaHnyf3T6IG0CRKIhO-oIYkCcqG4U4kyg0QKATPwDEwCqXKcMhimc4keMmYAdiRwH0llIo3QwBoUuKenqFutK3uGsBRGGANP4DZl0CajSorUKce1MHGsz1Hk12f5tv0HxnK3NBd_3L9EB94KPqiK0ivUbeqNvUb7-qNZvdc3wXJf9JKbHA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA46BT2pOPG3OXjN1mZZm3orm2PDrZQxYbeRnzKQTmqr_74v2aZ48CD0ENrQpO-1fN9L3teH0D1LYqko1URS0yEsYgERkkMriLQRgBjSrotNxFnG5_Mk34jVvRbGGOOTz0zLNf1evl6p2i2VtV1Z9A4cu2ivyxgN1nKtje43DJJ2P-3B-8ScAIV2W9vuvwqneNwYHP1zxGPU_FHg4fwbW07QjilOkfD-NOUDTjGQRPlqsCg0Hrv4-tMvcWIXTRZ2-VKX_vJ0mk6IAyqN89EEp0oByviNdQxkFfezDI9yN1DlM7KKJnoePM56Q7IpkUAEfEkVCSXQCxlZGUrdCQXn8ASOgwmgVTaiDKZpbajAWhqARwD7EVSEQnMFvEFCgHqGGsWqMOcIC6651nCHyMQM-iRUCh5baSPFdRCoC9R09lm8rf-Csdia5vKP83foYDibjBfjUfZ0hQ6dR1yKFaXXqFGVtblB--qjWr6Xt96LXzUTnmM
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2025+62nd+ACM%2FIEEE+Design+Automation+Conference+%28DAC%29&rft.atitle=Guarder%3A+A+Stable+and+Lightweight+Reconfigurable+RRAM-based+PIM+Accelerator+for+DNN+IP+Protection&rft.au=Lin%2C+Ning&rft.au=Li%2C+Yi&rft.au=Li%2C+Jiankun&rft.au=Yang%2C+Jichang&rft.date=2025-06-22&rft.pub=IEEE&rft.spage=1&rft.epage=7&rft_id=info:doi/10.1109%2FDAC63849.2025.11133133&rft.externalDocID=11133133