PhishSnap: Image-Based Phishing Detection Using Perceptual Hashing

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 $\mathbf{\text{PhishSnap}}$, 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 $\mathbf{\text{2024}}\mathbf{\text{dataset}}\mathbf{\text{of}}\mathbf{\text{10,000}}\mathbf{\text{URLs}}$ (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 $\mathbf{\text{0.79}}\mathbf{\text{accuracy}}$, $\mathbf{\text{0.76}}\mathbf{\text{precision}}$, and $\mathbf{\text{0.78}}\mathbf{\text{recall}}$, showing that visual similarity remains a viable anti-phishing measure. The entire inference process occurs locally, ensuring user privacy and minimal latency.