차분 프라이버시를 만족하는 안전한 GAN 기반 재현 데이터 생성 기술 연구
A Study on Synthetic Data Generation Based Safe Differentially Private GAN
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
많은 응용프로그램들로부터 양질의 서비스를 제공받기 위해서 데이터 공개는 필수적이다. 하지만 원본 데이터를그대로 공개할 경우 개인의 민감한 정보(정치적 성향, 질병 등)가 드러날 위험이 있기 때문에 원본 데이터가 아닌재현 데이터를 생성하여 공개함으로써 프라이버시를 보존하는 많은 연구들이 제안되어왔다. 그러나 단순히 재현 데이터를 생성하여 공개하는 것은 여러 공격들(연결공격, 추론공격 등)에 의해 여전히 프라이버시 유출 위험이 존재한다. 본 논문에서는 이러한 민감한 정보의 유출을 방지하기 위해, 재현 데이터 생성 모델로 주목받고 있는 GAN에최신 프라이버시 보호 기술인 차분 프라이버시를 적용하여 프라이버시가 보존되는 재현 데이터 생성 알고리즘을 제안한다. 생성 모델은 레이블이 있는 데이터의 효율적인 학습을 위해 CGAN을 사용하였고, 데이터의 유용성 측면을고려하여 기존 차분 프라이버시보다 프라이버시가 완화된 Rényi 차분 프라이버시를 적용하였다. 그리고 생성된 데이터의 유용성에 대한 검증을 다양한 분류기를 통해 실시하고 비교분석하였다.
Abstract
The publication of data is essential in order to receive high quality services from many applications. However, if theoriginal data is published as it is, there is a risk that sensitive information (political tendency, disease, ets.) may reveal. Therefore, many research have been proposed, not the original data but the synthetic data generating and publishing toprivacy preserve. but, there is a risk of privacy leakage still even if simply generate and publish the synthetic data byvarious attacks (linkage attack, inference attack, etc.). In this paper, we propose a synthetic data generation algorithm inwhich privacy preserved by applying differential privacy the latest privacy protection technique to GAN, which is drawingattention as a synthetic data generative model in order to prevent the leakage of such sensitive information. The generativemodel used CGAN for efficient learning of labeled data, and applied Rényi differential privacy, which is relaxation ofdifferential privacy, considering the utility aspects of the data. And validation of the utility of the generated data isconducted and compared through various classifiers.
참고문헌 (24)
- Buczak, Anna L., "Data-driven approach for creating synthetic electronic medical records", BMC medical informatics and decision making, 10(1), pp.59~ (2010)
- McLachlan, S., "Using the caremap with health incidents statistics for generating the realistic synthetic electronic healthcare record", IEEE International Conference on Healthcare Informatics (ICHI). 2016 IEEE, pp.439~448 (2016)
- Choi, E., "Generating multi-label discrete patient records using generative adversarial networks", arXiv preprint arXiv:1703.06490, ~ (2017)
- Narayanan, A, "Robust de-anonymization of larg sparse datasets", 2008 IEEE Symposium on Security and Privacy, pp.111~125 (2008), IEEE
- Sweeney, L., "Matching known patients to health records in Washington State data", Available at SSRN 2289850, ~ (2013)
- Dwork, C., "Calibrating noise to sensitivity in private data analysis", Journal of Privacy and Confidentiality, 7(3), pp.17~51 (2016)
- Dwork, C, "Differential privacy: A survey of results", International conference on theory and applications of models of computation, pp.1~19 (2008), Springer
- Bowen, C. M., "Comparative study of differentially private data synthesis methods", arXiv preprint arXiv: 1602.01063, ~ (2016)
- Liu, F., "Model-based differentially private data synthesis", arXiv preprint arXiv:1606.08052, ~ (2016)
- Li, H., "Differentially private synthesization of multi-dimensional data using copula functions, In Advances in database technology: proceedings", International conference on extending database technology, 2014, pp.475~ (2014), NIH Public Access
- Zhang, J., "Privbayes: Private data release via bayesian networks", ACM Transactions on Database Systems (TODS), 42(4), pp.1~41 (2017)
- Abay, N. C., "Privacy preserving synthetic data release using deep learning", Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp.510~526 (2018), Springer
- Jordon, J., "PATE-GAN: Generating synthetic data with differential privacy guarantees", International Conference on Learning Representations (2018)
- Song, S., "Stochastic gradient descent with differentially private updates", 2013 IEEE Global Conference on Signal and Information Processing, pp.245~248 (2013), IEEE
- Abadi, M., "Deep learning with differential privacy", Proceedings of the 2016 ACM SIGSAC Confernece on Computer and Communications Security, pp.308~318 (2016)
- Mironov, I., "Rényi differential privacy", 2017 IEEE 30th Computer Security Foundations Symposium (CSF), pp.263~275 (2017), IEEE
- Goodfellow, I., "Generative adversarial nets", Advances in neural information processing systems, pp.2672~2680 (2014)
- Mirza, M, "Conditional generative adversarial nets", arXiv preprint arXiv:1411.1784, ~ (2014)
- Dwork, C., "The algorihmic foundations of differential privacy", Foundations and Trends in Theoretical Computer Science, 9(3-4), pp.211~407 (2014)
- Mironov, I., "Rényi Differential Privacy of the Sampled Gauusian Mechnism", arXiv preprint arXiv:1908.10530, ~ (2019)
- Dal Pozzolo, A., "Calibrating probability with undersampling for unbalanced calssification", 2015IEEE Symposium Series on Computational Intelligence, pp.159~166 (2015), IEEE
- Fernandes, K., "Transfer learning with partial observability applied to cervical cancer screening", Iberian conference on pattern recognition and image analysis, pp.243~250 (2017), Springer
- "UCI machine learning repository" (2007)[URL]