Privacy-Preserved Approximate Classification Based on Homomorphic Encryption

Wu, Ting; Chen, Yuanfang; Fan, Xingyue

doi:10.3390/mca24040092

Cited by 4 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [40], the authors encoded the inputs to the comparator as bits and employed a BGV/TFHE cryptosystem to achieve secure decision tree evaluation. More recently, Xiao et al [41] proposed to replace the comparison function by a 24-degree Chebyshev polynomial approximation of the sigmoid function to securely evaluate decision trees using FHE.…”

Section: Related Workmentioning

confidence: 99%

Efficient Encrypted Inference on Ensembles of Decision Trees

Sarpatwar¹,

Nandakumar²,

Ratha³

et al. 2021

Preprint

View full text Add to dashboard Cite

Data privacy concerns often prevent the use of cloud-based machine learning services for sensitive personal data. While homomorphic encryption (HE) offers a potential solution by enabling computations on encrypted data, the challenge is to obtain accurate machine learning models that work within the multiplicative depth constraints of a leveled HE scheme. Existing approaches for encrypted inference either make ad-hoc simplifications to a pre-trained model (e.g., replace hard comparisons in a decision tree with soft comparators) at the cost of accuracy or directly train a new depth-constrained model using the original training set. In this work, we propose a framework to transfer knowledge extracted by complex decision tree ensembles to shallow neural networks (referred to as DTNets) that are highly conducive to encrypted inference. Our approach minimizes the accuracy loss by searching for the best DTNet architecture that operates within the given depth constraints and training this DTNet using only synthetic data sampled from the training data distribution. Extensive experiments on real-world datasets demonstrate that these characteristics are critical in ensuring that DTNet accuracy approaches that of the original tree ensemble. Our system is highly scalable and can perform efficient inference on batched encrypted (134 bits of security) data with amortized time in milliseconds. This is approximately three orders of magnitude faster than the standard approach of applying soft comparison at the internal nodes of the ensemble trees.

show abstract

Section: Related Workmentioning

confidence: 99%