Riazi, M. Sadegh ; Weinert, Christian ; Tkachenko, Oleksandr ; Songhori, Ebrahim M. ; Schneider, Thomas ; Koushanfar, Farinaz (2018)
Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications.
13. ACM Asia Conference on Information, Computer and Communications Security (ASIACCS'18). Incheon Republic of Korea (04.06.2018-04.06.2018)
doi: 10.1145/3196494.3196522
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
We present Chameleon, a novel hybrid (mixed-protocol) framework for secure function evaluation (SFE) which enables two parties to jointly compute a function without disclosing their private inputs. Chameleon combines the best aspects of generic SFE protocols with the ones that are based upon additive secret sharing. In particular, the framework performs linear operations in the ring $\mathbbZ _2^l $ using additively secret shared values and nonlinear operations using Yao's Garbled Circuits or the Goldreich-Micali-Wigderson protocol. Chameleon departs from the common assumption of additive or linear secret sharing models where three or more parties need to communicate in the online phase: the framework allows two parties with private inputs to communicate in the online phase under the assumption of a third node generating correlated randomness in an offline phase. Almost all of the heavy cryptographic operations are precomputed in an offline phase which substantially reduces the communication overhead. Chameleon is both scalable and significantly more efficient than the ABY framework (NDSS'15) it is based on. Our framework supports signed fixed-point numbers. In particular, Chameleon's vector dot product of signed fixed-point numbers improves the efficiency of mining and classification of encrypted data for algorithms based upon heavy matrix multiplications. Our evaluation of Chameleon on a 5 layer convolutional deep neural network shows 133x and 4.2x faster executions than Microsoft CryptoNets (ICML'16) and MiniONN (CCS'17), respectively.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2018 |
| Autor(en): | Riazi, M. Sadegh ; Weinert, Christian ; Tkachenko, Oleksandr ; Songhori, Ebrahim M. ; Schneider, Thomas ; Koushanfar, Farinaz |
| Art des Eintrags: | Bibliographie |
| Titel: | Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications |
| Sprache: | Englisch |
| Publikationsjahr: | Juni 2018 |
| Verlag: | ACM |
| Buchtitel: | ASIACCS '18: Proceedings of the 2018 on Asia Conference on Computer and Communications Security |
| Veranstaltungstitel: | 13. ACM Asia Conference on Information, Computer and Communications Security (ASIACCS'18) |
| Veranstaltungsort: | Incheon Republic of Korea |
| Veranstaltungsdatum: | 04.06.2018-04.06.2018 |
| DOI: | 10.1145/3196494.3196522 |
| URL / URN: | https://encrypto.de/papers/RWTSSK18.pdf |
| Kurzbeschreibung (Abstract): | We present Chameleon, a novel hybrid (mixed-protocol) framework for secure function evaluation (SFE) which enables two parties to jointly compute a function without disclosing their private inputs. Chameleon combines the best aspects of generic SFE protocols with the ones that are based upon additive secret sharing. In particular, the framework performs linear operations in the ring $\mathbbZ _2^l $ using additively secret shared values and nonlinear operations using Yao's Garbled Circuits or the Goldreich-Micali-Wigderson protocol. Chameleon departs from the common assumption of additive or linear secret sharing models where three or more parties need to communicate in the online phase: the framework allows two parties with private inputs to communicate in the online phase under the assumption of a third node generating correlated randomness in an offline phase. Almost all of the heavy cryptographic operations are precomputed in an offline phase which substantially reduces the communication overhead. Chameleon is both scalable and significantly more efficient than the ABY framework (NDSS'15) it is based on. Our framework supports signed fixed-point numbers. In particular, Chameleon's vector dot product of signed fixed-point numbers improves the efficiency of mining and classification of encrypted data for algorithms based upon heavy matrix multiplications. Our evaluation of Chameleon on a 5 layer convolutional deep neural network shows 133x and 4.2x faster executions than Microsoft CryptoNets (ICML'16) and MiniONN (CCS'17), respectively. |
| Freie Schlagworte: | Engineering;E4 |
| ID-Nummer: | TUD-CS-2018-0049 |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Praktische Kryptographie und Privatheit DFG-Sonderforschungsbereiche (inkl. Transregio) DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche Profilbereiche Profilbereiche > Cybersicherheit (CYSEC) LOEWE LOEWE > LOEWE-Zentren LOEWE > LOEWE-Zentren > CRISP - Center for Research in Security and Privacy 20 Fachbereich Informatik > EC SPRIDE DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche > SFB 1119: CROSSING – Kryptographiebasierte Sicherheitslösungen als Grundlage für Vertrauen in heutigen und zukünftigen IT-Systemen |
| Hinterlegungsdatum: | 05 Mär 2018 21:51 |
| Letzte Änderung: | 30 Jul 2024 10:51 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum