blaze blazing fast privacy preserving machine learning
play

BLAZE: BLAZING FAST PRIVACY-PRESERVING MACHINE LEARNING ARPITA PATRA - PowerPoint PPT Presentation

Sep 02, 2022 •1.85k likes •2.46k views

BLAZE: BLAZING FAST PRIVACY-PRESERVING MACHINE LEARNING ARPITA PATRA AND AJITH SURESH Ajith Suresh CrIS Lab, IISc https://www.csa.iisc.ac.in/~cris Outline q Secure Multi-party Computation (MPC) q MPC for small number of parties (3PC) q Our

  1. BLAZE: BLAZING FAST PRIVACY-PRESERVING MACHINE LEARNING ARPITA PATRA AND AJITH SURESH Ajith Suresh CrIS Lab, IISc https://www.csa.iisc.ac.in/~cris

  2. Outline q Secure Multi-party Computation (MPC) q MPC for small number of parties (3PC) q Our Efficient BLAZE Protocol (Results) q Privacy Preserving Machine Learning (PPML) AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  3. Secure Multi-party Computation (MPC) [Yao’82] ü A set of parties with private inputs wish to compute some joint function of their inputs. ü Goals of MPC: Correctness – Parties should correctly evaluate the function § output. Privacy – Nothing more than the function output should be § revealed AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  4. Secure Multi-party Computation (MPC) [Yao’82] ü A set of parties with private inputs wish to compute some joint function of their inputs. ü Goals of MPC: Correctness – Parties should correctly evaluate the function § Trusted output. Third Party Privacy – Nothing more than the function output should be § revealed AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  5. Secure Multi-party Computation (MPC) [Yao’82] ü A set of parties with private inputs wish to compute some joint function of their inputs. ü Goals of MPC: Correctness – Parties should correctly evaluate the function § Trusted output. Third Party Privacy – Nothing more than the function output should be § revealed AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  6. Secure Multi-party Computation (MPC) [Yao’82] ü A set of parties with private inputs wish to compute some joint function of their inputs. ü Goals of MPC: Correctness – Parties should correctly evaluate the function § MPC output. Privacy – Nothing more than the function output should be § revealed AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  7. Secure Multi-party Computation (MPC) [Yao’82] ADVERSARY • Semi – honest: • Follows the protocol but tries to learn more MPC • Malicious: • Can arbitrarily deviate from the protocol AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  8. Secure Multi-party Computation (MPC) [Yao’82] ADVERSARY • Semi – honest: • Follows the protocol but tries to learn more MPC • Malicious: • Can arbitrarily deviate from the protocol Malicious Corruption AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  9. MPC for small number of parties Ø Efficiency and Simplicity [MRZ15,AFLNO16,FLNW17,CGMV17] AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  10. MPC for small number of parties Ø Efficiency and Simplicity [MRZ15,AFLNO16,FLNW17,CGMV17] Ø Our focus: MPC with 3 parties AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  11. MPC for small number of parties Ø Efficiency and Simplicity [MRZ15,AFLNO16,FLNW17,CGMV17] Ø Our focus: MPC with 3 parties Ø Corruption : honest majority AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  12. MPC for small number of parties Ø Efficiency and Simplicity [MRZ15,AFLNO16,FLNW17,CGMV17] Ø Our focus: MPC with 3 parties Ø Corruption : honest majority q Majority of the parties are honest q 3PC – at most 1 corruption AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  13. MPC for small number of parties Ø Efficiency and Simplicity [MRZ15,AFLNO16,FLNW17,CGMV17] Ø Our focus: MPC with 3 parties Ø Corruption : honest majority Ø Outsourced Computation AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  14. MPC for small number of parties Ø Efficiency and Simplicity [MRZ15,AFLNO16,FLNW17,CGMV17] Ø Our focus: MPC with 3 parties Ø Corruption : honest majority Ø Outsourced Computation Ø Pre-processing Model AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  15. MPC for small number of parties Ø Efficiency and Simplicity [MRZ15,AFLNO16,FLNW17,CGMV17] Ø Our focus: MPC with 3 parties Ø Corruption : honest majority Ø Outsourced Computation Ø Pre-processing Model Pre-processing phase § AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  16. MPC for small number of parties Ø Efficiency and Simplicity [MRZ15,AFLNO16,FLNW17,CGMV17] Ø Our focus: MPC with 3 parties Ø Corruption : honest majority Ø Outsourced Computation Ø Pre-processing Model Pre-processing phase § q Data-independent Computation q Relatively slow and expensive AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  17. MPC for small number of parties Ø Efficiency and Simplicity [MRZ15,AFLNO16,FLNW17,CGMV17] Ø Our focus: MPC with 3 parties Ø Corruption : honest majority Ø Outsourced Computation Ø Pre-processing Model Pre-processing phase § Online Phase § AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  18. MPC for small number of parties Ø Efficiency and Simplicity [MRZ15,AFLNO16,FLNW17,CGMV17] Ø Our focus: MPC with 3 parties Ø Corruption : honest majority Ø Outsourced Computation Ø Pre-processing Model Pre-processing phase § q Minimized communication Online Phase § q Blazing fast AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  19. BLAZE PROTOCOL AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  20. BLAZE Protocol S 0 S 1 S 2 AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  21. BLAZE Protocol S 0 S 1 S 2 AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  22. BLAZE Protocol S 0 S 1 S 2 AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  23. BLAZE Protocol S 0 S 1 S 2 AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  24. BLAZE Protocol S 0 S 1 S 2 AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  25. BLAZE Protocol S 0 S 1 S 2 AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  26. BLAZE Protocol Communication Cost per !"#$: &. ( Multiplication Gate (malicious) BLAZE : https://eprint.iacr.org/2020/042 AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  27. BLAZE Protocol Pre-processing Online Ref Security (#elements) (#elements) Araki et al’17 12 9 Abort Communication Cost per !"#$: &. ( Multiplication Gate (malicious) BLAZE : https://eprint.iacr.org/2020/042 AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  28. BLAZE Protocol Pre-processing Online Ref Security (#elements) (#elements) Araki et al’17 12 9 Abort ASTRA 21 4 Fair Communication Cost per !"#$: &. ( Multiplication Gate (malicious) BLAZE : https://eprint.iacr.org/2020/042 AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  29. BLAZE Protocol Pre-processing Online Ref Security (#elements) (#elements) Araki et al’17 12 9 Abort ASTRA 21 4 Fair Boneh et al’19 0 3 Abort Communication Cost per !"#$: &. ( Multiplication Gate (malicious) BLAZE : https://eprint.iacr.org/2020/042 AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  30. BLAZE Protocol Pre-processing Online Ref Security (#elements) (#elements) Araki et al’17 12 9 Abort ASTRA 21 4 Fair Boneh et al’19 0 3 Abort BLAZE 3 3 Fair Communication Cost per !"#$: &. ( Multiplication Gate (malicious) BLAZE : https://eprint.iacr.org/2020/042 AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  31. Privacy Preserving Machine Learning (PPML) Model Query Parameters Result ML Algorithm Alice Bob (Model Owner) (Client) Privacy ?? AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  32. Privacy Preserving Machine Learning (PPML) Model Query Parameters Result ML Algorithm Alice Bob (Model Owner) (Client) Query AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  33. Privacy Preserving Machine Learning (PPML) Model Query Parameters Result ML Algorithm Alice Bob (Model Owner) (Client) Model Parameters AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  34. Solution ?? MPC ML AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  35. MPC MEETS ML AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  36. Privacy Preserving Machine Learning (PPML) Model Query MPC Parameters Result ML Algorithm Alice Bob (Model Owner) (Client) Use MPC to achieve privacy AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  37. MLaaS (3PC Servers) Query Model Parameters Result Alice Bob (Model Owner) (Client) SECURE OUTSOURCED SETTING (SOC) 26-02-2020 AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC

  38. Logistic Regression Neural Networks Linear Regression ML ALGORITHMS CONSIDERED AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

  39. PPML using MPC: Hurdles to Clear Secure Dot Product AJITH SURESH | CRYPTOGRAPHY AND INFORMATION SECURITY LAB ,CSA, IISC 26-02-2020

Recommend

New Directions in Privacy- preserving Machine Learning Kamalika Chaudhuri University of

New Directions in Privacy- preserving Machine Learning Kamalika Chaudhuri University of

New Directions in Privacy- preserving Machine Learning Kamalika Chaudhuri University of California, San Diego Sensitive Data Medical Records Genetic Data Search Logs AOL Violates Privacy AOL Violates Privacy Netflix Violates Privacy [NS08]

957 views • 92 slides
Blazing Fast CIS 541 Numerical Methods Computers are extremely fast at performing simple

Blazing Fast CIS 541 Numerical Methods Computers are extremely fast at performing simple

Blazing Fast CIS 541 Numerical Methods Computers are extremely fast at performing simple arithmetic. Machine Representation of Numbers Count from one to 1,000,000,000,000 by one - or - Execute on a Pentium-4 2GHz machine:

247 views • 11 slides
Approximate Homomorphic Encryption and Privacy Preserving Machine Learning Jung Hee Cheon (SNU,

Approximate Homomorphic Encryption and Privacy Preserving Machine Learning Jung Hee Cheon (SNU,

Approximate Homomorphic Encryption and Privacy Preserving Machine Learning Jung Hee Cheon (SNU, CryptoLab) Thanks to YongSoo Song, Kiwoo Lee, Andrey KIM Outline 1. Homomorphic Encryption 2. HEAAN 3. Bootstrapping of HEAAN 4. Toolkit for

981 views • 50 slides
Differential Privacy Machine Learning Li Xiong Big Data + Machine Learning + Machine

Differential Privacy Machine Learning Li Xiong Big Data + Machine Learning + Machine

CS573 Data Privacy and Security Differential Privacy Machine Learning Li Xiong Big Data + Machine Learning + Machine Learning Under Adversarial Settings Data privacy/confidentiality attacks membership attacks, model inversion

3.44k views • 63 slides
Privacy-preserving Neural Representations of Text Maximin Coavoux Shashi Narayan Shay B.

Privacy-preserving Neural Representations of Text Maximin Coavoux Shashi Narayan Shay B.

Privacy-preserving Neural Representations of Text Maximin Coavoux Shashi Narayan Shay B. Cohen University of Edinburgh ILCC EMNLP 2018 Brussels 1 / 15 Context: Privacy and Neural Networks Machine learning uses data (e.g. UGC)

481 views • 19 slides
Privacy in Machine Learning Fatemehsadat Mireshghallah ICLR2020 Privacy: A Major Concern for

Privacy in Machine Learning Fatemehsadat Mireshghallah ICLR2020 Privacy: A Major Concern for

Privacy in Machine Learning Fatemehsadat Mireshghallah ICLR2020 Privacy: A Major Concern for Machine Learning Graphics Adopted from The New York Times Privacy Project 2 Famous incidents - Anonymization - A Face Is Exposed for AOL

1.03k views • 7 slides
Fast & Faster Privacy-Preserving ML in Secure Hardware Enclaves Nick Hynes, Raymond

Fast & Faster Privacy-Preserving ML in Secure Hardware Enclaves Nick Hynes, Raymond

Fast & Faster Privacy-Preserving ML in Secure Hardware Enclaves Nick Hynes, Raymond Cheng, Dawn Song | UC Berkeley & Oasis Labs with support from the TVM team and community! Ideal: data providers pool data to train a large, complex

1.41k views • 58 slides
PINFER: PRIVACY-PRESERVING INFERENCE DPM 2019 Luxembourg Sep. 26, 2019 Marc Joye Fabien

PINFER: PRIVACY-PRESERVING INFERENCE DPM 2019 Luxembourg Sep. 26, 2019 Marc Joye Fabien

Innovation Centre PINFER: PRIVACY-PRESERVING INFERENCE DPM 2019 Luxembourg Sep. 26, 2019 Marc Joye Fabien Petitcolas MACHINE LEARNING AS A SERVICE GENERIC MODEL result Client Cloud (Server) 1 exchange of messages c 2019 OneSpan

588 views • 16 slides
Privacy Preserving Protocols Workshop on Cryptography for the Internet of Things Jens Hermans KU

Privacy Preserving Protocols Workshop on Cryptography for the Internet of Things Jens Hermans KU

Privacy Preserving Protocols Privacy Preserving Protocols Workshop on Cryptography for the Internet of Things Jens Hermans KU Leuven - COSIC 20 November 2012 Privacy Preserving Protocols Introduction Cryptography in Daily Life RFID Privacy

1.04k views • 60 slides
SECURITY, ADVERSARIAL SECURITY, ADVERSARIAL LEARNING, AND PRIVACY LEARNING, AND PRIVACY

SECURITY, ADVERSARIAL SECURITY, ADVERSARIAL LEARNING, AND PRIVACY LEARNING, AND PRIVACY

SECURITY, ADVERSARIAL SECURITY, ADVERSARIAL LEARNING, AND PRIVACY LEARNING, AND PRIVACY Christian Kaestner with slides from Eunsuk Kang Required reading: Hulten, Geoff. "Building Intelligent Systems: A Guide to Machine Learning

1.95k views • 113 slides
privacy-preserving decentralized learning of personalized models and collaboration graphs

privacy-preserving decentralized learning of personalized models and collaboration graphs

privacy-preserving decentralized learning of personalized models and collaboration graphs Aurlien Bellet (Inria) Includes work with: M. Tommasi, P. Vanhaesebrouck (University of Lille & Inria) R. Guerraoui, M. Taziki (EPFL) V. Zantedeschi

376 views • 33 slides
Differential Privacy Maria-Florina Balcan 04/22/2015 Learning and Privacy To do machine

Differential Privacy Maria-Florina Balcan 04/22/2015 Learning and Privacy To do machine

Machine Learning and Differential Privacy Maria-Florina Balcan 04/22/2015 Learning and Privacy To do machine learning, we need data. What if the data contains sensitive information? medical data, web search query data, salary data,

725 views • 15 slides
Machine Learning Machine Learning Fast & Slow Fast & Slow Suman Deb Roy Suman Deb Roy

Machine Learning Machine Learning Fast & Slow Fast & Slow Suman Deb Roy Suman Deb Roy

Machine Learning Machine Learning Fast & Slow Fast & Slow Suman Deb Roy Suman Deb Roy Lead Data Scientist @ betaworks bot www.rundexter.com /messaging www.poncho.is www.digg.com www.digg.com/messaging www.rundexter.com

781 views • 42 slides
ZX- TOWER Blazing Fast, Multi-Target, Easy To Use Hard Drive Wiper Who is Logicube? A

ZX- TOWER Blazing Fast, Multi-Target, Easy To Use Hard Drive Wiper Who is Logicube? A

ZX- TOWER Blazing Fast, Multi-Target, Easy To Use Hard Drive Wiper Who is Logicube? A leading manufacturer of eForensics data capture solutions and hard disk duplication systems Established in 1993 Headquarters in Chatsworth,

461 views • 28 slides
Privacy in Machine Learning Fatemehsadat Mireshghallah WiMLDS NeurIPS19 Meet-up Why is privacy a

Privacy in Machine Learning Fatemehsadat Mireshghallah WiMLDS NeurIPS19 Meet-up Why is privacy a

Privacy in Machine Learning Fatemehsadat Mireshghallah WiMLDS NeurIPS19 Meet-up Why is privacy a concern in ML? Patient History Genetic Data Search History Famous incidents - Anonymization - A Face Is Exposed for AOL Searcher No.

1.51k views • 17 slides
Privacy-preserving Information Sharing: Crypto Tools and Applications Emiliano De Cristofaro

Privacy-preserving Information Sharing: Crypto Tools and Applications Emiliano De Cristofaro

Privacy-preserving Information Sharing: Crypto Tools and Applications Emiliano De Cristofaro University College London (UCL) https://emilianodc.com Privacy-preserving what ? Parties with limited mutual trust willing or required to share

1.1k views • 66 slides
Privacy Advances in Machine Learning Systems Katharine Jarmul OReilly AI London kjamistan

Privacy Advances in Machine Learning Systems Katharine Jarmul OReilly AI London kjamistan

Privacy Advances in Machine Learning Systems Katharine Jarmul OReilly AI London kjamistan When did consumers become concerned about privacy and computing? From Understanding Privacy Concerns (1992) A 1990 Louis Harris survey commissioned

443 views • 30 slides
FEEL: A Federated Edge Learning System for Efficient and Privacy-Preserving Mobile Healthcare

FEEL: A Federated Edge Learning System for Efficient and Privacy-Preserving Mobile Healthcare

FEEL: A Federated Edge Learning System for Efficient and Privacy-Preserving Mobile Healthcare Yeting Guo, Zhiping Cai, Nong Xiao: National University of Defense Technology Fang Liu: Sun Yat-Sen University Li Chen: University of Louisiana at

247 views • 20 slides
Machine Learning for Compressive Privacy S.Y. Y. K Kung Prince ceton Un Univer ersi sity

Machine Learning for Compressive Privacy S.Y. Y. K Kung Prince ceton Un Univer ersi sity

Machine Learning for Compressive Privacy S.Y. Y. K Kung Prince ceton Un Univer ersi sity Machine Learning for Compressive Privacy Professor S.Y. Kung Email: kung@princeton.edu References: `Kernel Method and Machine

1.79k views • 142 slides
PRIVACY-PRESERVING PROCESSING OF RAW GENOMIC DATA Er Erman Ay man Ayday day , Jean Louis

PRIVACY-PRESERVING PROCESSING OF RAW GENOMIC DATA Er Erman Ay man Ayday day , Jean Louis

PRIVACY-PRESERVING PROCESSING OF RAW GENOMIC DATA Er Erman Ay man Ayday day , Jean Louis Raisaro, Urs Hengartner, Adam Molyneaux and Jean-Pierre Hubaux SEPTEMBER 2013 Raw data (short reads) Sequencing Samples machine SAM file 3 billion

555 views • 26 slides
Storage, Security, and Privacy in the age of ML Aleatha Parker-Wood, Ph.D. Machine Learning and

Storage, Security, and Privacy in the age of ML Aleatha Parker-Wood, Ph.D. Machine Learning and

Storage, Security, and Privacy in the age of ML Aleatha Parker-Wood, Ph.D. Machine Learning and Privacy Lead, Humu Who am I? Storage systems Ph.D. from UCSC Post-doc in a databases group Joined Symantec Research Labs.

286 views • 25 slides
Privacy-Preserving Computation with Trusted Computing via Scramble-then-Compute Hung Dang, Anh

Privacy-Preserving Computation with Trusted Computing via Scramble-then-Compute Hung Dang, Anh

Privacy-Preserving Computation with Trusted Computing via Scramble-then-Compute Hung Dang, Anh Dinh, Ee-Chien Chang, Beng Chin Ooi School of Computing National University of Singapore PETS 2017 Privacy-Preserving Computation with Trusted

477 views • 34 slides
Preserving the Privacy of Sensitive Relationships in Graph Data Motivation Valuable Data! No

Preserving the Privacy of Sensitive Relationships in Graph Data Motivation Valuable Data! No

Preserving the Privacy of Sensitive Relationships in Graph Data Motivation Valuable Data! No privacy breaches! Public Data Anonymization Data representation? Privacy breach? Value of data? Data publisher Privacy Analyst Work by: Elena

80 views • 3 slides
Collaborative Privacy Preserving Data Mining in Vertically Partitioned Databases Ehud Gudes

Collaborative Privacy Preserving Data Mining in Vertically Partitioned Databases Ehud Gudes

Collaborative Privacy Preserving Data Mining in Vertically Partitioned Databases Ehud Gudes Ben-Gurion University, Israel This talk presents joint work with Boris Rozenberg Talk Outline Motivation for Privacy-Preserving Distributed Data

1.48k views • 68 slides

More recommend