Fusion of SP-VAE and IMP-VAE for Proxy Attack Detection in ECommerce Systems
Abstract
With the rapid development of e-commerce, proxy attacks, as a covert and efficient means of fraud, have seriously damaged fair competition and consumer trust in the market. Traditional detection methods often have low efficiency and high false positive rates, so dealing with complex and variable switching attacks requires tremendous effort. This article delves into the issue of proxy attack detection in e-commerce and proposes an innovative solution that integrates SP-VAE and IMP-VAE algorithms. By optimizing the network structure and introducing advanced mechanisms, IMP-VAE enhances the model's ability to handle highdimensional sparse data and improves the accuracy of feature extraction. Specifically, the model first uses IMP-VAE to extract deep features from e-commerce transaction data to capture hidden information that is crucial for detecting trust attacks. Then, the extracted features are further screened and compressed using SPVAE sparse constraints to remove redundant information and highlight anomalous features. The attack detection model combining SP-VAE and IMP-VAE provides a new method for security protection research in the field of e-commerce, which has important theoretical significance and practical application value. The experimental results show that the SP-VAE algorithm achieved a detection accuracy of 92.3% in detecting users supporting attacks, which is about 15 percentage points higher than traditional methods.
Full Text:
PDFReferences
Wang XH. Research on referral system Support attack detection based on variational self-coding and supervised prototype networks. Nanjing University of Finance and Economics,2023.
Liu Y. Research on Dynamic Knowledge Graph recommendation system based on User behavior propagation. Beijing University of Civil Engineering and Architecture, 2023.
Zhang JB. Research on token attack detection based on feature analysis. North University of China,2022.
Wei XJ, Li HX. Research on Semi-supervised Detection of confusing-trust attacks against Commodity recommendation Systems. Science and Technology for Development, 2019, 16(09):1125-1133. (in Chinese)
Gupta BB, Gaurav A, Chui KT. Convolution neural network (CNN) based phishing attack detection model for e-business in enterprise information systems. Electronic Engineering and Computer Science, 2023, 23, 719-725.
Belghith A. Investigation on e-commerce platforms for tackling e-business security challenge. International Journal on Engineering Applications, 2022, 10(6).
Taherdoost H. E-Business Security and Control. E-business essentials: Building a successful online enterprise. Cham: Springer Nature Switzerland, 2023: 105-135.
Okoye CC, Nwankwo DO, Okeke NM, Nwankwo EE, Eze SU. Electronic commerce and sustainability of smes in anambra state. Malaysian E Commerce Journal. 2023, 7 (1): 32-41.
Shah A K, Singh P. A Systematic review on machine learning-based fraud detection system in E-commerce. Computer Science Engineering and Emerging Technologies, 2024, 552-557.
Yang Y, Yin Z. Accountancy for E-Business Enterprises based on cyber security. International Journal of Data Warehousing and Mining (IJDWM), 2023, 19(6): 1-17.
Yang C. Research on key technologies of recommendation system support attack defense and detection. Beijing University of Posts and Telecommunications, 20. (in Chinese
Yuan WQ. Research on Tow attack detection based on Time series. Tianjin University of Technology,2020.
Zhang X. Research on recommendation algorithm based on trusted neighbor. Nanjing University of Posts and Telecommunications,2020.
Zhang DY. Research on user payment fraud detection in E-commerce transactions. Shanghai University of Finance and Economics, 2023.
Ding ZX, Wang N. E-commerce payment security detection based on big data technology. Information and Computer (Theoretical Edition), 2023, 35(03):10-12.
Xu RQ, Zhang ZW, Sun HL. A new method for electronic commerce water force detection: Multi-relationship graph neural network with adaptive neighborhood precision sampling. Library and Information Knowledge, 2012, 39(06):35-44
Wang X. Research on fake score detection and reputation evaluation methods in e-commerce. Shandong University of Science and Technology, 2020.
Wang YH. Research on API model security design and testing of E-commerce system. Yanshan University, 2020.
Xujie Q. Research on loyalty prediction of e-commerce customer based on data mining. Applied Mathematics and Nonlinear Sciences, 2019, 8(2):721-732.
Xia D, Chen W, Li Y, Fu X. Research on the detection of privacy information sharing behaviour of e-commerce users based on big data. International Journal of Autonomous and Adaptive Communications Systems, 2022, 15(3):249-265.
Cheruku P, Kumar A. Study on the Detection of False Comments in Online Review of E-commerce Website. Journal of Research in Science and Engineering, 2019, 3(11).
Finance - Electronic Commerce; New Electronic Commerce Findings from South Asian University Described (A Survey of Figurative Language and Its Computational Detection in Online Social Networks. Internet Weekly News, 2019, 12.
Rodriguez-Ardura I, Meseguer-Artola A. Editorial: How to prevent, detect and control common method variance in electronic commerce research. Journal of Theoretical and Applied Electronic Commerce Research, 2019, 15(2):I-V.
Finance - Electronic Commerce; New Findings from Center for Research and Technology Hellas Update Understanding of Electronic Commerce (Detecting Cyberbullying and Cyberaggression in Social Media). Internet Business Newsweekly, 2020.
Changyup N, Hyun D B. A study on the prediction in transformation processes of e-business emerging technology gaps - focusing on hype cycles of South Korea and the U.S. The e-Business Studies, 2019, 20(6):89-103.
Finance - Electronic Commerce; Findings from W.M. Watanabe and Co-Authors Reveals New Information on Electronic Commerce (Layout Cross-platform and Cross-browser Incompatibilities Detection Using Classification of Dom Elements). Computers, Networks & Communications, 2019,
Zhang Q. Research on Visual design based on E-commerce platform of inspection and testing industry. Science and Technology and Innovation, 2019, (04):69-70+72.
RB/T 149-2018, Guidelines for the Management of Inspection and Testing E-commerce Platforms.
Zhang Wenyu. Detection of fake reviewers in E-commerce based on Behavior Analysis. Yunnan University, 2018.
Mackasare S, Chowdhury R S. An empirical study of factors affecting customer loyalty in e-business: a predictive study in selected states of India. International Journal of Electronic Customer Relationship Management, 2018, 11(3): 203-236.
DOI: https://doi.org/10.31449/inf.v49i8.6906
This work is licensed under a Creative Commons Attribution 3.0 License.