Chameleon

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 Z 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.

A Review of Deep Learning Security and Privacy Defensive Techniques

“…CryptoNets is basically developed by the Microsoft Research group, by introducing levelled Homomorphic Encryption (LHC). Due to nonlinear activation functions that cannot be achieved using LHE, the authors proposed that the activation functions are approached using polynomials of multiple degrees [41]. erefore, the neural network must be retrained in plain text with the same activation function to maintain good prediction accuracy.…”

“…Chameleon uses secret sharing for arithmetic and addition functions. It has offline and online phases like in MiniONN [41]. e offline computation provided more fast computation for prediction instead of the online phase.…”

Recent Advances in Practical Secure Multi-Party Computation

“…(1) Equality Check An equality check protocol Equality( x A , y A ) (e.g., [10], [40], [41]) outputs z B , where z = 1 iff x = y. A basic strategy for constructing Equality is as follows: we first compute t = x − y and then check all bits of t are 0 or not.…”

“…(2) Less-Than Comparison A less-than comparison protocol (Comparison( x A , y A )) outputs z B , where z = 1 iff the condition x < y holds (e.g., [10], [40], [41]). A basic strategy for constructing Comparison is to check the sign of x − y.…”

“…There are many research results on privacy-preserving data mining (start from [62], [63]) and secure machine learning (e.g., [12], [39], [41], [64], [65]). Research targets have varied, and recently there are many results on privacypreserving deep neural networks.…”