TPRPF: a preserving framework of privacy relations based on adversarial training for texts in big data

doi:10.1007/s11704-022-1653-0

Front. Comput. Sci.

2022, Vol. 16

Issue (4) : 164618 https://doi.org/10.1007/s11704-022-1653-0

LETTER

TPRPF: a preserving framework of privacy relations based on adversarial training for texts in big data

Yuhan CHAI, Zhe SUN, Jing QIU(

), Lihua YIN(

), Zhihong TIAN

Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou 510006, China

Download: PDF(1188 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Corresponding Author(s): Jing QIU,Lihua YIN

Just Accepted Date: 15 April 2022 Issue Date: 16 May 2022

Cite this article:

Yuhan CHAI,Zhe SUN,Jing QIU, et al. TPRPF: a preserving framework of privacy relations based on adversarial training for texts in big data[J]. Front. Comput. Sci., 2022, 16(4): 164618.

URL:

https://academic.hep.com.cn/fcs/EN/10.1007/s11704-022-1653-0
https://academic.hep.com.cn/fcs/EN/Y2022/V16/I4/164618

Fig.1 The primary learning task trains the text classifier through the text representations to predict the sentiment label; the privacy relations task trains the adversary classifier through the intercepted text representations to infer the privacy relations between users contained in the text representations

Fig.2 The architecture of TPRPF framework

Tab.1 Experimental results of ConvMS model

Tab.2 Experimental results of TPRPF framework

1	Y Li T Baldwin T Cohn. Towards robust and privacy-preserving text representation. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. 2018, 25– 30
2	M Coavoux S Narayan S B Cohen. Privacy-preserving neural representations of text. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2018, 1– 10
3	J Lang L Li W Chen D Zeng. Privacy protection in transformer-based neural network. In: Proceedings of 2019 IEEE International Conference on Intelligence and Security Informatics (ISI). 2019, 182– 184
4	M Friedrich A Köhn G Wiedemann C Biemann. Adversarial learning of privacy-preserving text representations for de-identification of medical records. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019, 5829– 5839
5	M Jaiswal E M Provost. Privacy enhanced multimodal neural representations for emotion recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 7985– 7993
6	J Deng J Guo N Xue S Zafeiriou. Arcface: additive angular margin loss for deep face recognition. In: Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019, 4685– 4694
7	A Li J Guo H Yang Y Chen. Deepobfuscator: adversarial training framework for privacy-preserving image classification. 2019, arXiv preprint arXiv: 1909.04126
8	X Han H Zhu P Yu Z Wang Y Yao Z Liu M Sun. FewRel: a large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation. In: Proceedings of 2018 Conference on Empirical Methods in Natural Language Processing. 2018, 4803– 4809
9	S Loria. Textblob Documentation. website, 2018

[1]

Download

Viewed

Full text

Abstract

Cited

Shared

Discussed