A Transformer-CNN-SVM Based Architecture for Legal Risk Assessment in Data Privacy Infringements
Abstract
Under the wave of digitalization, privacy rights and data protection face severe challenges. This study focuses on the application of artificial intelligence in this legal issue and constructs an intelligent legal privacy protection system (ILPPS). By integrating real data from multiple fields such as finance, e-commerce, social networking, medical care, and government affairs and corresponding legal provisions, an experimental system is built. Using accuracy, recall, and F1 value as evaluation indicators, ILPPS is compared with models such as C4.5, Naive Bayes, BERT-SVM, CNN-LSTM, and GRU-SVM. The experimental results show that ILPPS performs well on data sets in various fields. For example, in the financial field, the accuracy rate is 0.87, the recall rate is 0.84, and the F1 value is 0.85; comprehensive analysis of various fields shows that ILPPS has an average accuracy rate of 0.86, a recall rate of 0.83, and an F1 value of 0.84. This shows that ILPPS is significantly superior to traditional models in data privacy risk assessment and infringement judgment, providing enterprises and legal institutions with more effective data privacy protection tools, enriching the research in the intersection of computer technology and law, and promoting the healthy development of social digitalization.References
Majeed A, Hwang SO. When AI meets information privacy: the adversarial role of AI in data sharing Scenario. IEEE Access. 2023; 11:76177-95. DOI: 10.1109/access.2023.3297646
Villegas-Ch W, García-Ortiz J. Toward a comprehensive framework for ensuring security and privacy in artificial intelligence. Electronics. 2023; 12(18). DOI: 10.3390/electronics12183786
Zhao Y, Chen JJ. A survey on differential privacy for unstructured data content. ACM Computing Surveys. 2022; 54(10S). DOI: 10.1145/3490237
Ye XB, Yan YH, Li J, Jiang B. Privacy and personal data risk governance for generative artificial intelligence: A Chinese perspective. Telecommunications Policy. 2024; 48(10). DOI: 10.1016/j.telpol.2024.102851
Zhang F, Zhang YQ, Zhang XH. Desensitization method of meteorological data based on differential privacy protection. Journal of Cleaner Production. 2023; 389. DOI: 10.1016/j.jclepro.2023.136117
Goldsteen A, Saadi O, Shmelkin R, Shachor S, Razinkov N. AI privacy toolkit. Softwarex. 2023; 22. DOI: 10.1016/j.softx.2023.101352
Wang LH, Liu XQ, Shao W, Guan CX, Huang QH, Xu SJ, et al. A Blockchain-based privacy-preserving healthcare data sharing scheme for incremental updates. Symmetry-Basel. 2024; 16(1). DOI: 10.3390/sym16010089
1. Abbasi W, Mori P, Saracino A. Trading-Off privacy, utility, and Explainability in deep learning-based image data analysis. IEEE Transactions on Dependable and Secure Computing. 2025; 22(1):388-405. DOI: 10.1109/tdsc.2024.3400608
Wang YC, Liang XL, Hei XH, Ji WJ, Zhu L. Deep learning data privacy protection based on Homomorphic encryption in AIoT. Mobile Information Systems. 2021; 2021. DOI: 10.1155/2021/5510857
Amaral O, Abualhaija S, Torre D, Sabetzadeh M, Briand LC. AI-Enabled automation for completeness checking of privacy policies. IEEE Transactions on Software Engineering. 2022; 48(11):4647-74. DOI: 10.1109/tse.2021.3124332
Kiran A, Rubini P, Kumar SS. Comprehensive review of privacy, utility, and fairness offered by synthetic data. IEEE Access. 2025; 13:15795-811. DOI: 10.1109/access.2025.3532128
Xu JM, Hong NX, Xu ZN, Zhao Z, Wu C, Kuang K, et al. Data-Driven learning for data rights, data pricing, and privacy computing. Engineering. 2023; 25:66-76. DOI: 10.1016/j.eng.2022.12.008
Zheng Y, Chang CH, Huang SH, Chen PY, Picek S. An overview of trustworthy ai: advances in ip protection, privacy-preserving federated learning, security verification, and GAI safety alignment. IEEE Journal on Emerging and Selected Topics in Circuits and Systems. 2024; 14(4):582-607. DOI: 10.1109/jetcas.2024.3477348
Sun YY, Liu JJ, Wang JD, Cao YR, Kato N. When machine learning meets privacy in 6G: a survey. IEEE Communications Surveys and Tutorials. 2020; 22(4):2694-724. DOI: 10.1109/comst.2020.3011561
Xiong JB, Zhao MF, Bhuiyan MZA, Chen L, Tian YL. An AI-Enabled three-party game framework for guaranteed data privacy in mobile edge Crowdsensing of IoT. IEEE Transactions on Industrial Informatics. 2021; 17(2):922-33. DOI: 10.1109/tii.2019.2957130
Ge LN, Li HA, Wang X, Wang Z. A review of secure federated learning: Privacy leakage threats, protection technologies, challenges and future directions. Neurocomputing. 2023; 561. DOI: 10.1016/j.neucom.2023.126897
Zhou ZG, Wang Y, Yu X, Miao JZ. A Targeted privacy-preserving data publishing method based on Bayesian network. IEEE Access. 2022; 10:89555-67. DOI: 10.1109/access.2022.3201641
Rodríguez-Barroso N, Stipcich G, Jímenez-López D, Ruiz-Millán JA, Martínez-Cámara E, González-Seco G, et al. Federated learning and differential privacy: Software tools analysis, the Sherpa.ai framework FL and methodological guidelines for preserving data privacy. Information Fusion. 2020; 64:270-92.
Barnawi A, Chhikara P, Tekchandani R, Kumar N, Alzahrani B. A differentially privacy assisted federated learning scheme to preserve data privacy for IoMT applications. IEEE Transactions on Network and Service Management. 2024; 21(4):4686-700. DOI: 10.1109/tnsm.2024.3393969
Azam N, Michala L, Ansari S, Truong NB. Data privacy threat modelling for autonomous systems: A survey from the GDPR’s perspective. IEEE Transactions on Big Data. 2023; 9(2):388-414. DOI: 10.1109/tbdata.2022.3227336
El Mestari SZ, Lenzini G, Demirci H. Preserving data privacy in machine learning systems. Computers & Security. 2024; 137. DOI: 10.1016/j.cose.2023.103605
Chung KC, Chen CH, Tsai HH, Chuang YH. Social media privacy management strategies: A SEM analysis of user privacy behaviors. Computer Communications. 2021; 174:122-30. DOI: 10.1016/j.comcom.2021.04.012
Wang X, Liang Y. DBN FTLSTM: an optimized deep learning framework for speech and image recognition. Informatica. 2025; 49(20):119-136. DOI: 10.31449/inf.v49i20.8169.
Cheng S, Yang Q, Luo H. Design of neural network based online teaching interactive system in the context of multimedia assisted teaching. Informatica. 2024; 48(7): 53-62. DOI: 10.31449/inf.v48i7.5205.
DOI:
https://doi.org/10.31449/inf.v50i5.9175Downloads
Published
How to Cite
Issue
Section
License
Authors retain copyright in their work. By submitting to and publishing with Informatica, authors grant the publisher (Slovene Society Informatika) the non-exclusive right to publish, reproduce, and distribute the article and to identify itself as the original publisher.
All articles are published under the Creative Commons Attribution license CC BY 3.0. Under this license, others may share and adapt the work for any purpose, provided appropriate credit is given and changes (if any) are indicated.
Authors may deposit and share the submitted version, accepted manuscript, and published version, provided the original publication in Informatica is properly cited.
