# Towards Web Phishing Detection Limitations and Mitigation

arXiv: https://arxiv.org/abs/2204.00985 · HTML: https://mlsanity.com/paper/2204.00985/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 55 references that are in the map.
- First posted on arXiv 3 Apr 2022.

## Builds on (most cited first, 8 of 8)

- [URLNet: Learning a URL Representation with Deep Learning for Malicious URL Detection](https://mlsanity.com/paper/1802.03162/) (2018)
- [Advanced Evasion Attacks and Mitigations on Practical ML-Based Phishing Website Classifiers](https://mlsanity.com/paper/2004.06954/) (2020)
- [Malicious URL Detection using Machine Learning: A Survey](https://mlsanity.com/paper/1701.07179/) (2017)
- [DeltaPhish: Detecting Phishing Webpages in Compromised Websites](https://mlsanity.com/paper/1707.00317/) (2017)
- [Detecting Homoglyph Attacks with a Siamese Neural Network](https://mlsanity.com/paper/1805.09738/) (2018)
- [Characterizing Malicious URL Campaigns](https://mlsanity.com/paper/2108.12726/) (2021)
- [Email Summarization to Assist Users in Phishing Identification](https://mlsanity.com/paper/2203.13380/) (2022)
- [HTMLPhish: Enabling Phishing Web Page Detection by Applying Deep Learning Techniques on HTML Analysis](https://mlsanity.com/paper/1909.01135/) (2019)

## Built on by (most cited first, 5 of 5)

- [Web Content Filtering through knowledge distillation of Large Language Models](https://mlsanity.com/paper/2305.05027/) (2023)
- [Profiler: Profile-Based Model to Detect Phishing Emails](https://mlsanity.com/paper/2208.08745/) (2022)
- [PhishClone: Measuring the Efficacy of Cloning Evasion Attacks](https://mlsanity.com/paper/2209.01582/) (2022)
- [Small Language Models for Phishing Website Detection: Cost, Performance, and Privacy Trade-Offs](https://mlsanity.com/paper/2511.15434/) (2025)
- [A Gradient-Optimized TSK Fuzzy Framework for Explainable Phishing Detection](https://mlsanity.com/paper/2504.18636/) (2025)

## Abstract (arXiv)

Web phishing remains a serious cyber threat responsible for most data breaches. Machine Learning (ML)-based anti-phishing detectors are seen as an effective countermeasure, and are increasingly adopted by web-browsers and software products. However, with an average of 10K phishing links reported per hour to platforms such as PhishTank and VirusTotal (VT), the deficiencies of such ML-based solutions are laid bare. We first explore how phishing sites bypass ML-based detection with a deep dive into 13K phishing pages targeting major brands such as Facebook. Results show successful evasion is caused by: (1) use of benign services to obscure phishing URLs; (2) high similarity between the HTML structures of phishing and benign pages; (3) hiding the ultimate phishing content within Javascript and running such scripts only on the client; (4) looking beyond typical credentials and credit cards for new content such as IDs and documents; (5) hiding phishing content until after human interaction. We attribute the root cause to the dependency of ML-based models on the vertical feature space (webpage content). These solutions rely only on what phishers present within the page itself. Thus, we propose Anti-SubtlePhish, a more resilient model based on logistic regression. The key augmentation is the inclusion of a horizontal feature space, which examines correlation variables between the final render of suspicious pages against what trusted services have recorded (e.g., PageRank). To defeat (1) and (2), we correlate information between WHOIS, PageRank, and page analytics. To combat (3), (4) and (5), we correlate features after rendering the page. Experiments with 100K phishing/benign sites show promising accuracy (98.8%). We also obtained 100% accuracy against 0-day phishing pages that were manually crafted, comparing well to the 0% recorded by VT vendors over the first four days.