当前位置:首页 > 报告详情

不太可能的英雄:模拟光子神经网络作为内置对抗防御者的非理想性.pdf

上传人: 芦苇 编号:651824 2025-05-01 22页 2.26MB

1、The Unlikely Hero:Nonideality in Analog Photonic Neural Networks as Built-in Defender Against Adversarial Attacks1Haotian Lu,Ziang Yin,Partho Bhoumik,Sanmitra Banerjee,Krishnendu Chakrabarty,Jiaqi Gu1Arizona State UniversitySchool of Electrical,Computer and Energy Engineeringjiaqiguasu.edu|scopex-as

2、u.github.ioMarch 7,2025Photonic ML Accelerators2Evolve from electronics to heterogenous electronics-photonicsSource:Mitchell A.Nahmias,Bhavin J.Shastri,Alexander N.Tait,Thomas Ferreira de Lima and Paul R.Prucnal,“Neuromorphic photonics,”Optics&Photonics News,Jan 2018.Optical-electronic hybrid chips(

3、10 TOPS/W)Fully-optical chipsNeuromorphic photonics(1E6 TOPS/W)Energy Efficiency(TOPS/W)Compute Density(TOPS/mm2)Speed-of-light,Massive parallelism,low-powerpotential105Photonic AI System is Booming3Photonic Neural Network Trends in AcademiaSciRep17Nat.Photon17ASP-DAC20DATE20Nature19ASP-DAC19DATE21A

4、PR20Nature21HPCA20PhysRev19Nature21Nat.Comm.22Nat.Comm.22Science24Nanophotonics24Photonic Computing Chip+Optical InterconnectsFoundry/EPDA Support in IndustryElectronic-Photonic Design Automation ToolsPDK/Tape-out/HI/E-O Co-Packaging SupportGaps in Electronic-Photonic AI Eco-systems4EPIC AI ecosyste

5、m is in early stage,many new challengesReliabilityVariations+AttacksAccuracy loss95%60%Area/E-O Cost40200 2Large spatial footprintE-O/A-D conversion01010 01011 E-OO-EReconfigurabilityLack of versatilityfor diverse workloadsLow precision in encodingPrecision?Our concern in this paper Reliability is S

6、everely Challenged by Attack5Security problem is under-explored for AMS photonic AI hardwareSerious reliability concerns with two enemies?Malicious attack Hardware non-ideality+Bit-flip Attack in Photonic AI Hardware6Bit-flip(PBFA)Rakin+,ICCV19 poses great threat to Photonic AI HWWhite-box attack,ar

word格式文档无特别注明外均可编辑修改,预览文件经过压缩,下载原文更清晰!
三个皮匠报告文库所有资源均是客户上传分享,仅供网友学习交流,未经上传用户书面授权,请勿作商用。
本文提出了一种针对光子神经网络的新型防御框架,利用硬件非理想性作为内置防御机制,对抗恶意攻击和硬件中的变异。研究指出,光子AI硬件的安全性问题尚未得到充分探索,硬件的非理想性(如量化、稀疏性、芯片噪声等)可以天然地提高系统的鲁棒性。文章提出了一种联合的防御策略,包括:(1)基于量化的预攻击防御;(2)基于剪枝的后攻击恢复。该策略有效检测并纠正了被攻击的权重,实现了小于2%的准确度下降和约2%的内存开销。此外,文章还探讨了如何通过优化内存分配,使用户在保持高准确度的同时,最小化内存开销。研究显示,这种方法能够在不到1小时内搜索到有效的防御策略,并且能够在光子神经网络中实现83%至86.7%的准确度恢复。这一成果对比了现有的防御方法,突显了该策略在内存效率和防御效果上的优势。
"光子神经网络如何抵御恶意攻击?" "非理想性如何成为光子AI硬件的内在防御机制?" "光子AI硬件的安全性问题是否得到了足够的关注?"
客服
商务合作
小程序
服务号
折叠