Treiber, Amos ; Molina, Alejandro ; Weinert, Christian ; Schneider, Thomas ; Kersting, Kristian (2020)
CryptoSPN: Expanding PPML beyond Neural Networks.
2020 ACM SIGSAC Conference on Computer and Communications Security (CCS '20). virtual Conference (09.11.2020 - 13.11.2020)
doi: 10.1145/3411501.3419417
Conference or Workshop Item, Bibliographie
Abstract
The ubiquitous deployment of machine learning (ML) technologies has certainly improved many applications but also raised challenging privacy concerns, as sensitive client data is usually processed remotely at the discretion of a service provider. Therefore, privacy-preserving machine learning (PPML) aims at providing privacy using techniques such as secure multi-party computation (SMPC). Recent years have seen a rapid influx of cryptographic frameworks that steadily improve performance as well as usability, pushing PPML towards practice. However, as it is mainly driven by the crypto community, the PPML toolkit so far is mostly restricted to well-known neural networks (NNs). Unfortunately, deep probabilistic models rising in the ML community that can deal with a wide range of probabilistic queries and offer tractability guarantees are severely underrepresented. Due to a lack of interdisciplinary collaboration, PPML is missing such important trends, ultimately hindering the adoption of privacy technology. In this work, we introduce CryptoSPN, a framework for privacy-preserving inference of sum-product networks (SPNs) to significantly expand the PPML toolkit beyond NNs. SPNs are deep probabilistic models at the sweet-spot between expressivity and tractability, allowing for a range of exact queries in linear time. In an interdisciplinary effort, we combine techniques from both ML and crypto to allow for efficient, privacy-preserving SPN inference via SMPC. We provide CryptoSPN as open source and seamlessly integrate it into the SPFlow library (Molina et al., arXiv 2019) for practical use by ML experts. Our evaluation on a broad range of SPNs demonstrates that CryptoSPN achieves highly efficient and accurate inference within seconds for medium-sized SPNs.
| Item Type: | Conference or Workshop Item |
|---|---|
| Erschienen: | 2020 |
| Creators: | Treiber, Amos ; Molina, Alejandro ; Weinert, Christian ; Schneider, Thomas ; Kersting, Kristian |
| Type of entry: | Bibliographie |
| Title: | CryptoSPN: Expanding PPML beyond Neural Networks |
| Language: | English |
| Date: | 9 November 2020 |
| Publisher: | ACM |
| Book Title: | PPMLP'20: Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practi |
| Event Title: | 2020 ACM SIGSAC Conference on Computer and Communications Security (CCS '20) |
| Event Location: | virtual Conference |
| Event Dates: | 09.11.2020 - 13.11.2020 |
| DOI: | 10.1145/3411501.3419417 |
| Abstract: | The ubiquitous deployment of machine learning (ML) technologies has certainly improved many applications but also raised challenging privacy concerns, as sensitive client data is usually processed remotely at the discretion of a service provider. Therefore, privacy-preserving machine learning (PPML) aims at providing privacy using techniques such as secure multi-party computation (SMPC). Recent years have seen a rapid influx of cryptographic frameworks that steadily improve performance as well as usability, pushing PPML towards practice. However, as it is mainly driven by the crypto community, the PPML toolkit so far is mostly restricted to well-known neural networks (NNs). Unfortunately, deep probabilistic models rising in the ML community that can deal with a wide range of probabilistic queries and offer tractability guarantees are severely underrepresented. Due to a lack of interdisciplinary collaboration, PPML is missing such important trends, ultimately hindering the adoption of privacy technology. In this work, we introduce CryptoSPN, a framework for privacy-preserving inference of sum-product networks (SPNs) to significantly expand the PPML toolkit beyond NNs. SPNs are deep probabilistic models at the sweet-spot between expressivity and tractability, allowing for a range of exact queries in linear time. In an interdisciplinary effort, we combine techniques from both ML and crypto to allow for efficient, privacy-preserving SPN inference via SMPC. We provide CryptoSPN as open source and seamlessly integrate it into the SPFlow library (Molina et al., arXiv 2019) for practical use by ML experts. Our evaluation on a broad range of SPNs demonstrates that CryptoSPN achieves highly efficient and accurate inference within seconds for medium-sized SPNs. |
| Uncontrolled Keywords: | Engineering; E4 |
| Additional Information: | Privacy Preserving Machine Learning in Practice (PPMLP'20) – CCS 2020 Workshop |
| Divisions: | 20 Department of Computer Science 20 Department of Computer Science > Cryptography and Privacy Engineering (ENCRYPTO) DFG-Collaborative Research Centres (incl. Transregio) DFG-Collaborative Research Centres (incl. Transregio) > Collaborative Research Centres DFG-Graduiertenkollegs DFG-Graduiertenkollegs > Research Training Group 2050 Privacy and Trust for Mobile Users Profile Areas Profile Areas > Cybersecurity (CYSEC) LOEWE LOEWE > LOEWE-Zentren LOEWE > LOEWE-Zentren > CRISP - Center for Research in Security and Privacy DFG-Collaborative Research Centres (incl. Transregio) > Collaborative Research Centres > CRC 1119: CROSSING – Cryptography-Based Security Solutions: Enabling Trust in New and Next Generation Computing Environments |
| Date Deposited: | 28 Sep 2020 07:32 |
| Last Modified: | 29 Jul 2024 12:26 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Send an inquiry |
Options (only for editors)
 |
Show editorial Details |
Drucken
Impressum