The proliferation of online network services has led to a steady rise in gambling-related activities, posing serious challenges to cyber governance and public security. Despite significant efforts by law enforcement agencies to curb online gambling, its dynamic and covert nature continues to hinder effective regulation. In this study, we propose a novel identification framework that leverages multimodal signals—including webpage text, visual content, and embedded image text—to detect gambling websites with high precision. Our approach integrates these heterogeneous data sources into a unified model, achieving robust representation and classification across diverse website structures. Extensive experiments on a domain-specific dataset demonstrate that our method significantly outperforms traditional baselines, reaching an accuracy of 99.3%. This work contributes an effective and scalable technical solution to assist real-world gambling crime detection and opens new directions for multimodal modeling in security applications.
XieLYuGL. Research on the governance strategies of cross-border online gambling. Journal of China Criminal Police College2024: 33–45.
2.
Ministry of Public Security: Press conference on combating and rectifying cross - border online gambling crimes and typical cases. (2020) (Accessed: 15-May-2025).
3.
AgbefuREHoriYSakuraiK. Domain information based blacklisting method for the detection of malicious webpages. Int J Cyber-Secur Digital Forensics2013; 2(2): 36–48.
4.
Vikalwe ShakraniKMathew KanyangararaNParowaPT, et al.A deep learning model for face recognition in presence of mask. Acta inform Malays2022; 6(2): 43–46.
5.
KimTChoS. Deep learning for cyber security: a survey. IEEE Communica- tions Surveys & Tutorials2020; 22(1): 204–246.
6.
ZhaoLWangM.Detection of gambling websites using convolutional neural networks. In: Proceedings of the International Conference on Computational Science (ICCS), pp. 423–434. Springer (2019).
7.
BaltrušaitisTAhujaCMorencyLP. Multimodal machine learning: a survey and taxonomy. IEEE Trans Pattern Anal Mach Intell2019; 41(2): 423–443.
8.
SinghRKumarV. Multimodal deep learning for cyber threat detection: a review. ACM Comput Surv2021; 54(3): 62.
9.
ZhangYZhouMXuZ. Multimodal large language models: a survey. arXiv preprint arXiv:2306.12337. 2023.
10.
SahooDLiuCHoiSCH. Malicious URL detection using machine learning: a survey. arXiv preprint arXiv:1701.071792017. https://arxiv.org/abs/1701 (Accessed: 25-January-2024).
11.
MaCDuXCaoL, et al.Burst-analysis website fingerprinting attack based on deep neural network. J Comput Res Dev2020; 57(4): 746–766.
12.
XuXZhouSShengM, et al.Research on fraud website recognition tech- nology based on convolutional neural network model. Modern Computer2021; 27(29): 10–17.
13.
TanPWenN. A study on a method of identifying HTTPS illegal websites. Internet World2022; 2022(4): 36–39.
14.
ShukangYChaoyouFSiruiZ, et al.A survey on multimodal large language models. Computing Research Repository2024; 11(12): 403.
15.
LiJLiuDLiuY, et al.BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.125972023.
16.
ZhuDChenJShenX, et al.MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.105922023.
17.
WangHLiuZJiangK, et al.Interpretable multimodal fake news detection based on dual co-attention networks. Journal of Computing and Cybersecurity Engineering2023; 2(1): 1–17.
18.
AhmedAQureshiAMajeedA, et al.Navigating the ethical landscape of ChatGPT integration in scientific research: review of challenges and recommendations. Journal of Computing and Cybersecurity Engineering2023; 2(2): 45–57.
19.
DuzhenZYahanYJiahuaD, et al.MM-LLMs: recent advances in multimodal large language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), Findings of ACL, August 11–16, 2024,Bangkok, Thailand. Association for Computational Linguistics, pp. 12401–12430.
20.
LiC.Implementation and performance comparison of web page automation processing based on BeautifulSoup+requests and selenium crawlers. Modern Information Technology2021; 5(16): 10–12.
21.
WangC.Research on prompt word engineering for large-scale art image generation. Acta Graph2024; 45(6): 1243–1255.
22.
DevlinJChangM-WLeeK, et al. BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2019), June 2–7, 2019,Minneapolis, Minnesota, USA. Association for Computational Linguistics, pp. 4171–4186.
23.
LiuZLinYCaoY, et al.Swin Transformer: hierarchical vision transformer using shifted windows. In: Proceeding IEEE international conference on computer vision (ICCV), Montreal, QC, Canada, 10–17 October 2021, pp. 9992–10002. IEEE.
24.
ZhuHTanYWWeiWT. Few-shot aspect-based sentiment analysis via fine-tuning large language models. Journal of Modern Information2025.
25.
HeKZhangXRenS, et al.Deep residual learning for image recognition. In: Proceeding IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016, pp. 770–778. IEEE.
26.
WangWTianYYangL, et al.Open-Qwen2VL: compute-efficient pre- training of fully-open multimodal LLMs on academic resources. arXiv preprint arXiv:2504.00595 (2025). https://arxiv.org/abs/2504.00595 (Accessed: 21-May-2025).
27.
ZadehAChenM-HPoriaS, et al.Tensor fusion network for multimodal sentiment analysis. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP 2017), September 7–11, 2017,Copenhagen, Denmark. Association for Computational Linguistics, pp. 1103–1114.
