High-performance secure multi-party computation for data mining applications

By Dan Bogdanov, Margus Niitsoo, Tomas Toft, Jan Willemson. 2012

213 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

Citations in the corpus

Machine Learning Models that Remember Too Much (2017, background): “ining data. SecureMLenvironments. Startingwith[49],therehasbeenmuch research on using secure multi-party computation to enable several parties to create a joint model on their separate datasets, e.g. [11, 16, 22]. A protocol for distributed, privacy-preserving deep learning was proposed in [67]. Aba”
SecureNN: 3-Party Secure Computation for Neural Network Training (2019, background): “Secure multi-party computation (MPC) [8, 17, 25, 40] and specifically 3-party computation [6, 9, 10, 14, 18, 23, 28, 32] provide a generic solution for the above problem.”
Combining Secret Sharing and Garbled Circuits for Efficient Private IEEE 754 Floating-Point Computations (2015, unknown): “However, we will focus on our instantiation built into the Sharemind MPC platform [8].”
From Keys to Databases - Real-World Applications of Secure Multi-Party Computation (2018, unknown): “shared3p 787 1 bit 8/16/32/64 bits 8/16/32/64 bits 32/64 bits 32/64 bits [26]”
Automated Synthesis of Optimized Circuits for Secure Computation (2015, methodology): “Additionally, we present benchmarks for matrix multiplication, but here we are slower than previous approaches of [BNTW12, ZSB13, DSZ15].”
Combining Differential Privacy and Secure Multiparty Computation (2015, methodology): “While implementing the DP mechanisms on top of the SMC framework, we had to come up with novel SMC protocols for some subtasks.”
High-Throughput Semi-Honest Secure Three-Party Computation with an Honest Majority (2016, methodology): “We remark that our method for generating correlated randomness can be used to reduce the number of elements sent in the Sharemind protocol from 5 to 2 and to reduce the number of communication rounds to 1.”
SoK: General Purpose Compilers for Secure Multi-Party Computation (2019, background): “broad potential for practical applications, ranging from general computations of secure statistical analysis [22], [23], [25], [52], [53], [54], [55], [96], to more domainspecific uses like financial oversight [2], [21], [26], [58], biomedical computations [35], [32], [75], [84], [82], [85], [132] a”
Rmind: A Tool for Cryptographically Secure Statistical Analysis (2016, methodology): “Further operations in this protection domain kind require more complex protocols, as described in [30], [36].”
ABY2.0: Improved Mixed-Protocol Secure Two-Party Computation (2020, methodology): “An equivalent formulation of the problem [19, 82] is to check if all the bits of a− b are 0 or not.”
SecureNN: Efficient and Private Neural Network Training (2018, methodology): “Since we are in the 3-server setting, another tempting option might be to use techniques from Sharemind [9] and its successors [10, 14] that use techniques of bit extraction to perform the”