EUVIMEDEUVIMED entdecken
Crossref

From ML to LLM: Evaluating the Robustness of Phishing Web Page Detection Models against Adversarial Attacks

Aditya Kulkarni, Vivek Balachandran, Dinil Mon Divakaran, Tamal Das

Digital Threats: Research and Practice · 30.06.2025 · 6 (2) · 1-25

DOI: 10.1145/3737295 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Digital Threats: Research and Practice, online erschienen am 26.06.2025. Verfasst von Aditya Kulkarni und 3 weiteren Autor:innen. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 52 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Phishing attacks attempt to deceive users into stealing sensitive information, posing a significant cybersecurity threat. Advances in Machine Learning (ML) and Deep Learning (DL) have led to the development of numerous phishing web page detection solutions, but these models remain vulnerable to adversarial attacks. Evaluating their robustness against adversarial phishing web pages is essential. Existing tools contain datasets of pre-designed phishing web pages for a limited number of brands and lack diversity in phishing features. To address these challenges, we develop PhishOracle , a tool that generates adversarial phishing web pages by embedding diverse phishing features into legitimate web pages. We evaluate the robustness of three existing task-specific models—Stack model, VisualPhishNet, and Phishpedia—against PhishOracle -generated adversarial phishing web pages and observe a significant drop in their detection rates. In contrast, a Multimodal Large Language Model (MLLM)-based phishing detector demonstrates stronger robustness against these adversarial attacks but still is prone to evasion. Our findings highlight the vulnerability of phishing detection models to adversarial attacks, emphasizing the need for more robust detection approaches. Furthermore, we conduct a user study to evaluate whether PhishOracle -generated adversarial phishing web pages can deceive users. The results show that many of these phishing web pages evade not only existing detection models but also users.

Zitieren

APA

Kulkarni, A., Balachandran, V., Divakaran, D. M., & Das, T. (2025). From ML to LLM: Evaluating the Robustness of Phishing Web Page Detection Models against Adversarial Attacks. Digital Threats: Research and Practice, 6(2), 1-25. https://doi.org/10.1145/3737295

Vancouver

Kulkarni A, Balachandran V, Divakaran DM, Das T. From ML to LLM: Evaluating the Robustness of Phishing Web Page Detection Models against Adversarial Attacks. Digital Threats: Research and Practice. 2025;6(2):1-25. doi:10.1145/3737295

BibTeX
@article{Kulkarni2025,
  author = {Kulkarni, Aditya and Balachandran, Vivek and Divakaran, Dinil Mon and Das, Tamal},
  title = {From ML to LLM: Evaluating the Robustness of Phishing Web Page Detection Models against Adversarial Attacks},
  journal = {Digital Threats: Research and Practice},
  year = {2025},
  volume = {6},
  number = {2},
  pages = {1--25},
  doi = {10.1145/3737295}
}
Kostenlos starten →