BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260730T152640Z
LOCATION:
DTSTART;TZID=America/Los_Angeles:20260728T174700
DTEND;TZID=America/Los_Angeles:20260728T174700
UID:dac_DAC 2026_sess317_RESEARCH1185@linklings.com
SUMMARY:CPA-BNN: A Secure and Efficient CIM and PUF Architecture for BNN A
 ccelerator
DESCRIPTION:Li Ni, Jinwei Pu, Xijun Huang, Wenhong Ma, Zhenyu Wang, Lei Li
 ao, Wanli Chang, and You Meng (Hunan University)\n\nBinary neural networks
  (BNNs) have emerged as promising models for lightweight intelligent infer
 ence by binarizing inputs and weights. Compute in memory (CIM) architectur
 es, which reduce data movements through in-situ operations, have become a 
 strong candidate for BNN accelerators. However, prior works often overlook
  the security of the model, leaving BNN weights exposed in memory cells an
 d vulnerable to threats such as cloning, tampering, and reverse engineerin
 g. This work proposes CPA-BNN, a secure BNN CIM architecture based on resi
 stive random access memory (RRAM). We propose a 4T2R RRAM cell design whic
 h implements in-situ encryption and ciphertext convolution operations to p
 rotect the weights. In addition, an in-memory batch normalization (BN) sch
 eme is proposed to optimize area overhead and improve compute density. Bes
 ides, we propose an intrinsic physical unclonable function (PUF) entropy e
 xtraction method and a current tilt-based masking stratege, enabling relia
 ble key extraction within a unified array. The results show that CPA-BNN a
 chieves ~100% key reliability and effectively prevents model attacks. Comp
 ared to state-of-the-art SRAM/NVM BNN schemes, CPA-BNN achieves >1.4× comp
 ute density and >1.6× storage density improvement.\n\nTrack: EDA7-II. Phys
 ical Design and Verification, Design\n\nSession Chairs: Christian Pilato (
 Politecnico di Milano); Mohsen Imani (University of California, Irvine); F
 lavio Ponzina (San Diego State University); Amin Farshidi (Cadence Design 
 Systems, Inc.); Yonggan Fu (Georgia Institute of Technology, NVIDIA); Dimi
 trios Tsaras (Huawei, Hong Kong University of Science and Technology (HKUS
 T)); Anh Nguyen (Fujitsu Limited); Ruiyang Qin (Villanova University); Jil
 iang Zhang (Hunan University); Meng Li (Peking University); and Rassul Bai
 ramkulov (Advanced Micro Devices (AMD))\n\n
END:VEVENT
END:VCALENDAR