Primer: Fast Private Transformer Inference on Encrypted Data

It is increasingly important to enable privacy-preserving inference for cloud services based on Transformers. Post-quantum cryptographic techniques, e.g., fully homomorphic encryption (FHE), and multi-party computation (MPC), are popular methods to support private Transformer inference. However, exi...

Full description

Saved in:
Bibliographic Details
Published in:2023 60th ACM/IEEE Design Automation Conference (DAC) pp. 1 - 6
Main Authors: Zheng, Mengxin, Lou, Qian, Jiang, Lei
Format: Conference Proceeding
Language:English
Published: IEEE 09.07.2023
Subjects:
Computational modeling
Cryptographic Protocol
Cryptography
Design automation
Fully Homomorphic Encryption
Multi-party computation
Natural language processing
Private Inference
Solids
Transformer
Transformers
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract It is increasingly important to enable privacy-preserving inference for cloud services based on Transformers. Post-quantum cryptographic techniques, e.g., fully homomorphic encryption (FHE), and multi-party computation (MPC), are popular methods to support private Transformer inference. However, existing works still suffer from prohibitively computational and communicational overhead. In this work, we present, Primer, to enable a fast and accurate Transformer over encrypted data for natural language processing tasks. In particular, Primer is constructed by a hybrid cryptographic protocol optimized for attention-based Transformer models, as well as techniques including computation merge and tokens-first ciphertext packing. Comprehensive experiments on encrypted language modeling show that Primer achieves state-of-the-art accuracy and reduces the inference latency by 90.6% ∼ 97.5% over previous methods.
AbstractList It is increasingly important to enable privacy-preserving inference for cloud services based on Transformers. Post-quantum cryptographic techniques, e.g., fully homomorphic encryption (FHE), and multi-party computation (MPC), are popular methods to support private Transformer inference. However, existing works still suffer from prohibitively computational and communicational overhead. In this work, we present, Primer, to enable a fast and accurate Transformer over encrypted data for natural language processing tasks. In particular, Primer is constructed by a hybrid cryptographic protocol optimized for attention-based Transformer models, as well as techniques including computation merge and tokens-first ciphertext packing. Comprehensive experiments on encrypted language modeling show that Primer achieves state-of-the-art accuracy and reduces the inference latency by 90.6% ∼ 97.5% over previous methods.
Author Lou, Qian
Zheng, Mengxin
Jiang, Lei
Author_xml – sequence: 1
  givenname: Mengxin
  surname: Zheng
  fullname: Zheng, Mengxin
  email: zhengme@iu.edu
  organization: Indiana University Bloomington
– sequence: 2
  givenname: Qian
  surname: Lou
  fullname: Lou, Qian
  email: qian.lou@ucf.edu
  organization: University of Central Florida
– sequence: 3
  givenname: Lei
  surname: Jiang
  fullname: Jiang, Lei
  email: jiang60@iu.edu
  organization: Indiana University Bloomington
BookMark eNo1j91KAzEUhCMoqHXfQCQv0PXkd0_Em7JttVDQi3pdkuwJLGi2ZBehb--CejUM8zHM3LLLPGRi7EFALQS4x_WqNdZJV0uQqhYgddMId8Eq1zhUBpRUGsU1q8axD2DBoAarb9jze-m_qDzxrR8nPptvPxE_FJ_HNJQ54bucqFCOxIfMNzmW82mijq_95O_YVfKfI1V_umAf282hfV3u31527Wq_9NLBtEQlIaSErkMXuxgMUmeNJK1RdolSE50goxwK47EJESXaMJNoIYACpxbs_re3J6LjaV7sy_n4f1L9ACGeSXE
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/DAC56929.2023.10247719
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Xplore
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798350323481
EndPage 6
ExternalDocumentID 10247719
Genre orig-research
GroupedDBID 6IE
6IH
ACM
ALMA_UNASSIGNED_HOLDINGS
CBEJK
RIE
RIO
ID FETCH-LOGICAL-a290t-8320bff89d89cdcb58ed652e4482dfef7c91e539815a87bc8286b9cd860b03093
IEDL.DBID RIE
ISICitedReferencesCount 5
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001073487300054&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:47:47 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a290t-8320bff89d89cdcb58ed652e4482dfef7c91e539815a87bc8286b9cd860b03093
PageCount 6
ParticipantIDs ieee_primary_10247719
PublicationCentury 2000
PublicationDate 2023-July-9
PublicationDateYYYYMMDD 2023-07-09
PublicationDate_xml – month: 07
  year: 2023
  text: 2023-July-9
  day: 09
PublicationDecade 2020
PublicationTitle 2023 60th ACM/IEEE Design Automation Conference (DAC)
PublicationTitleAbbrev DAC
PublicationYear 2023
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssib060584064
Score 2.3564305
Snippet It is increasingly important to enable privacy-preserving inference for cloud services based on Transformers. Post-quantum cryptographic techniques, e.g.,...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Computational modeling
Cryptographic Protocol
Cryptography
Design automation
Fully Homomorphic Encryption
Multi-party computation
Natural language processing
Private Inference
Solids
Transformer
Transformers
Title Primer: Fast Private Transformer Inference on Encrypted Data
URI https://ieeexplore.ieee.org/document/10247719
WOSCitedRecordID wos001073487300054&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV05T8MwFLagYmACRBC3PLA6OKdtxILaRrBUGYrUrfLxLLGkVZoi8e-x3aSIgYHN8iHLlz7b733vQ-hBamq4MjmRDt1JnqWKCLcNiGQO67VUNhMqiE2w2YwvFqLuyeqBCwMAwfkMYp8Mtnyz0lv_VeZOeJoz5oN8HjJW7shaw-bx5j0HTnnPAk6oeJy8jIvSwX_sJcLjofEvGZWAItXJP_s_RdEPHw_Xe6Q5QwfQnKPn2kfmb59wJTedK_YyZYDnw0UUWvy2b7xq8LTR7dfa3S_xRHYyQu_VdD5-Jb0WApGpoB1xB48qa7kwXGijVcHBlEUK7nWVGguWaZFAkQmeFJIzpT07XLmavKQqWDsv0KhZNXCJcMK1t46WJuMqp5pLVtJc08yyQlkH6Fco8kNfrnfhLpbDqK__yL9Bx36Cgw-ruEWjrt3CHTrSn93Hpr0Pi_QNfJeRlw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3LSgMxFA1SBV2pWPFtFm5TMzPJJBE30nZosZYuKnRX8gQ30zKdCv69SdqpuHDhLuQBeXJucnPuAeBBamy4MgRJj-6IZKlCwm8DJJnHei2Vy4SKYhNsPOazmZhsyeqRC2OtjZ_PbCckoy_fLPQ6PJX5E54SxkKQz31KSIo3dK1m-wQHn4cnsuUBJ1g89l66NPcGQCeIhHea5r-EVCKOFMf_7MEJaP8w8uBkhzWnYM-WZ-B5EmLzV0-wkKvaFwehMgunjSlqKzjcNV6UsF_q6mvpLUzYk7Vsg_eiP-0O0FYNAclU4Br5o4eVc1wYLrTRinJrcppaf79KjbOOaZFYmgmeUMmZ0oEfrnxNnmMV_Z3noFUuSnsBYMJ18I_mJuOKYM0lyzHROHOMKuch_RK0w9Dny03Ai3kz6qs_8u_B4WD6NpqPhuPXa3AUJjv-aBU3oFVXa3sLDvRn_bGq7uKCfQNDipTe
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=2023+60th+ACM%2FIEEE+Design+Automation+Conference+%28DAC%29&rft.atitle=Primer%3A+Fast+Private+Transformer+Inference+on+Encrypted+Data&rft.au=Zheng%2C+Mengxin&rft.au=Lou%2C+Qian&rft.au=Jiang%2C+Lei&rft.date=2023-07-09&rft.pub=IEEE&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FDAC56929.2023.10247719&rft.externalDocID=10247719