1.Key Laboratory of Aerospace Information Security and Trusted Computing,Ministry of Education,School of Cyber Science and Engineering,Wuhan University,Wuhan 430072,Hubei,China
2.The State Key Laboratory of Blockchain and Data Security,Zhejiang University,Hangzhou 310058,Zhejiang,China
3.China United Network Telecommunications Corporation Zhejiang Branch,Hangzhou 310058,Zhejiang,China
A phishing toolkit is a collection of code resources widely used for the rapid, bulk deployment of phishing websites. By identifying the specific toolkit used by a phishing website, one can efficiently detect other sites deployed using the same toolkit, supporting precise detection and attribution analysis of phishing websites. However, existing methods mostly rely on manual deployment of toolkits and suffer from low accuracy. To address these issues, this paper proposes a phishing website detection method based on phishing toolkit fingerprinting. This method extracts fingerprints of the toolkit from its directory structure, text, and resources without the need for deployment, and employs different methods to calculate fingerprint similarity. Comparing the proposed method with three baseline methods, experiments demonstrate that without deploying the toolkit, the proposed method achieves a phishing website detection accuracy of 99.5%, which is comparable to the best baseline method. Furthermore, it achieves a phishing toolkit identification accuracy of 80.5% (an improvement of 26.2 percentage points over the best baseline) and a phishing toolkit family identification accuracy of 85.4% (an improvement of 8.6 percentage points). Ablation experiments show that the directory structure fingerprint is the core component, while text and resource fingerprints provide effective complementarity. Integrating all three features significantly improves the performance of toolkit and family identification.
该数据集包含12 719个正常网站样本和164个钓鱼网站样本。对于正常网站部分,本文从Tranco Top 1M流行网站列表[20]中选取排名前20 000的网站,使用Selenium[21]控制Chrome for Testing(v134.0.6998.35)无头浏览器[22]访问并保存网页快照,快照内容包括HTML代码、JavaScript、CSS、图片等资源。因部分网站存在反爬机制,经人工筛选后,最终获得12 719个正常网站样本。
BOZKIRA S, DALGICF C, AYDOSM. GramBeddings: A new neural network for URL based identification of phishing web pages through N-gram embeddings[J]. Computers & Security, 2023, 124: 102964. DOI:10.1016/j.cose.2022.102964 .
[2]
ZHENGF A, YANQ, LEUNGV C M, et al. HDP-CNN: Highway deep pyramid convolution neural network combining word-level and character-level representations for phishing website detection[J]. Computers & Security, 2022, 114: 102584. DOI:10.1016/j.cose.2021.102584 .
ZHONGW K, WANGT, ZHANGG X. Phishing URL detection method based on component segmentation[J]. Journal of Cyber Security, 2025, 10(1): 130-142. DOI:10.19363/J.cnki.cn10-1380/tn.2025.01.10 (Ch ).
[5]
PURWANTOR W, PAL A, BLAIRA, et al. PhishSim: Aiding phishing website detection with a feature-free tool[J]. IEEE Transactions on Information Forensics and Security, 2022, 17: 1497-1512. DOI:10.1109/TIFS.2022.3164212 .
ZHANGS R, YANZ W, DONGK J, et al. Phishing detection algorithm based on attention and feature fusion[J]. Chinese Journal of Network and Information Security, 2024, 10(4): 123-131. DOI:10.11959/j.issn.2096-109x.2024058 (Ch ).
[8]
LIUR F, LINY, YANGX D, et al. Inferring phishing intention via webpage appearance and dynamics: A deep vision based approach[DB/OL].[2025-08-02].
[9]
LINY, LIUR F, DIVAKARAND M, et al. Phishpedia: A hybrid deep learning based approach to visually identify phishing webpages[DB/OL].[2025-08-02].
WENW P, ZHUY F, LÜZ H, et al. Brand-specific phishing expansion and detection solutions[J]. Netinfo Security, 2023, 23(12): 1-9 (Ch).
[12]
LIM K, PARKJ, KIMD. Phishing vs. legit: Comparative analysis of client-side resources of phishing and target brand websites[C]//Proceedings of the ACM Web Conference 2024. New York :ACM, 2024: 1756-1767. DOI:10.1145/3589334.3645535 .
[13]
ZHANGP H, OESTA, CHOH, et al. CrawlPhish: Large-scale analysis of client-side cloaking techniques in phishing[C]//2021 IEEE Symposium on Security and Privacy (SP). New York: IEEE Press, 2021: 1109-1124. DOI:10.1109/SP40001.2021.00021 .
[14]
BIJMANSH L J, BOOIJT M, SCHWEDERSKYA, et al. Catching phishers by their bait: Investigating the Dutch phishing landscape through phishing kit detection[C]// In 30th USENIX Security Symposium (USENIX Security 21). Berkeley: USENIX Association, 2021: 3757-3774.
[15]
LEEW, HUR J, KIMD. Beneath the phishing scripts: A script-level analysis of phishing kits and their impact on real-world phishing websites[C]//Proceedings of the 19th ACM Asia Conference on Computer and Communications Security. New York: ACM, 2024: 856-872. DOI:10.1145/3634737.3657013 .
[16]
TANAKAS, MATSUNAKAT, YAMADAA, et al. Phishing site detection using similarity of website structure[C]//2021 IEEE Conference on Dependable and Secure Computing (DSC). New York: IEEE Press, 2021: 1-8. DOI:10.1109/DSC49826.2021.9346256 .
[17]
SPARCK JONESK. A statistical interpretation of term specificity and its application in retrieval[J]. Journal of Documentation, 1972, 28(1): 11-21. DOI: 10.1108/eb026526 .
[18]
PAWLIKM, AUGSTENN. Efficient computation of the tree edit distance[J]. ACM Transactions on Database Systems, 2015, 40(1): 1-40. DOI:10.1145/2699485 .
[19]
JACCARDP. The distribution of the flora in the Alpine zone[J]. The New Phytologist, 1912, 11(2): 37-50. DOI: 10.1111/j.1469-8137.1912.tb05611.x .