PhishSnap: Image-Based Phishing Detection Using Perceptual Hashing
This addresses phishing threats for online users by offering a privacy-preserving detection method, though it is incremental as it builds on visual similarity approaches.
The paper tackled the problem of phishing detection by proposing PhishSnap, an on-device system using perceptual hashing to identify visually similar phishing webpages, achieving 0.79 accuracy, 0.76 precision, and 0.78 recall on a dataset of 10,000 URLs.
Phishing remains one of the most prevalent online threats, exploiting human trust to harvest sensitive credentials. Existing URL- and HTML-based detection systems struggle against obfuscation and visual deception. This paper presents \textbf{PhishSnap}, a privacy-preserving, on-device phishing detection system leveraging perceptual hashing (pHash). Implemented as a browser extension, PhishSnap captures webpage screenshots, computes visual hashes, and compares them against legitimate templates to identify visually similar phishing attempts. A \textbf{2024 dataset of 10,000 URLs} (70\%/20\%/10\% train/validation/test) was collected from PhishTank and Netcraft. Due to security takedowns, a subset of phishing pages was unavailable, reducing dataset diversity. The system achieved \textbf{0.79 accuracy}, \textbf{0.76 precision}, and \textbf{0.78 recall}, showing that visual similarity remains a viable anti-phishing measure. The entire inference process occurs locally, ensuring user privacy and minimal latency.