Abstract
The darknet has been a notorious hub for illegal and criminal activities. One of the major challenges in identifying criminals involved in darknet market transactions is the presence of multi-identity vendors, who operate under different accounts to evade detection. Existing methods have limitations such as incomplete feature characterization, imprecise data annotation, and an inability to analyze across markets. In this paper, we propose a new approach to address these issues. Rich information of traded goods is collected from 21 currently existing English darknet markets as experimental data. Our method entails extracting text and image features and computing the writing style of suppliers. Subsequently, the feature dimension is reduced and pseudo labeling is applied to improve label accuracy. Further, four types of data about vendors are mapped onto a heterogeneous information network to characterize potential relationships among darknet vendors. By leveraging the graph neural network algorithm and Siamese neural networks, the link relationship between different accounts is predicted to determine whether they belong to the same supplier. The experimental results demonstrate the effectiveness of our proposed method in identifying different accounts belonging to the same supplier with a maximum accuracy of 99.75% and a recall rate of 99.09%.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Clarke, I., Sandberg, O., Wiley, B., Hong, T.W.: Freenet: a distributed anonymous information storage and retrieval system. In: Workshop on Design Issues in Anonymity and Unobservability (2000)
Me, G., Pesticcio, L., Spagnoletti, P.: Discovering hidden relations between tor marketplaces users. In: 2017 IEEE 15th International Conference on Dependable, Autonomic and Secure Computing, 15th International Conference on Pervasive Intelligence and Computing, 3rd International Confernce on Big Data Intelligence and Computing and Cyber Science and Technology Congress(DASC/PiCom/DataCom/CyberSciTech), pp. 494–501 (2017)
Kumar, R., et al.: edarkfind: unsupervised multi-view learning for sybil account detection. In: Proceedings of The Web Conference 2020 (2020)
Wang, X., Peng, P., Wang, C., Wang, G.: You are your photographs: detecting multiple identities of vendors in the darknet marketplaces. In: Proceedings of the 2018 on Asia Conference on Computer and Communications Security (2018)
Zhang, Y., et al.: Your style your identity: leveraging writing and photography styles for drug trafficker identification in darknet markets over attributed heterogeneous information network. In: The World Wide Web Conference (2019)
Mosteller, F., Wallace, D.L.: A comparative study of discrimination methods applied to the authorship of the disputed federalist papers (2016)
Jeziorowski, S.: Dark vendor profilng (2020)
Ekambaranathan, A.: Using stylometry to track cybercriminals in darknet forums (2018)
Zhang, Y., et al.: dstyle-gan: generative adversarial network based on writing and photography styles for drug identification in darknet markets. In: Annual Computer Security Applications Conference (2020)
Netsec-SJTU: darkweb-market-dataset-2021. Website (2022). https://github.com/Netsec-SJTU/darkweb-market-dataset-2021
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. ArXiv abs/1810.04805 (2019)
Vaswani, A., et al.: Attention is all you need. ArXiv abs/1706.03762 (2017)
Le, Q.V., Mikolov, T.: Distributed representations of sentences and documents. In: ICML (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
Shlens, J.: A tutorial on principal component analysis. ArXiv abs/1404.1100 (2014)
Benton, A., Arora, R., Dredze, M.: Learning multiview embeddings of twitter users. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (vol. 2: Short Papers) (2016)
Lee, D.H.: Pseudo-label : the simple and efficient semi-supervised learning method for deep neural networks (2013)
Yang, Y., Lichtenwalter, R., Chawla, N.: Evaluating link prediction methods. Knowl. Inf. Syst. 45, 751–782 (2014)
Jaccard, P.: The distribution of the flora in the alpine zone.1. New Phytol. 11, 37–50 (1912)
Hamilton, W.L., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: NIPS (2017)
Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 1, pp. 539–546 (2005)
Acknowledgment
This work is supported by the National Key Research and Development Program of China (No.2020YFB1807500)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zou, F., Hu, Y., Xu, W., Wu, Y. (2023). Link Prediction-Based Multi-Identity Recognition of Darknet Vendors. In: Wang, D., Yung, M., Liu, Z., Chen, X. (eds) Information and Communications Security. ICICS 2023. Lecture Notes in Computer Science, vol 14252. Springer, Singapore. https://doi.org/10.1007/978-981-99-7356-9_19
Download citation
DOI: https://doi.org/10.1007/978-981-99-7356-9_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-7355-2
Online ISBN: 978-981-99-7356-9
eBook Packages: Computer ScienceComputer Science (R0)