← Back to all news
arXiv AI By Basil Sajid Shaikh

A Computer Vision Approach to Visual Fraud Detection in Phishing Websites Using YOLOv8

Read the original on arXiv AI →

The paper presents a visual phishing detection system that treats rendered webpages as images, using a YOLOv8 convolutional neural network to classify full-page screenshots as phishing or legitimate. It achieves 92% accuracy, processes a screenshot in about 100 ms, and reduces false positives by 11% after targeted data augmentation. The authors detail dataset creation, augmentation, model architecture, training, and discuss how this visual approach complements existing URL- and content-based defenses.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 3

Swin Meets EfficientNet: Lightweight Architectures for GAN-Based Face Forensics

The paper presents lightweight architectures for detecting GAN-generated synthetic faces, comparing a compact Swin Transformer, pre‑trained Swin‑Tiny and Swin‑Small models, and a hybrid EfficientNet‑B0 + Swin Transformer. Using the 140K Real and Fake Faces dataset, the hybrid model achieved 99% accuracy and 99.44% recall on 5,000 test images, outperforming both pure Swin variants and a CNN‑only baseline. The study demonstrates that combining hierarchical CNN features with shifted‑window self‑attention yields an efficient, computationally lightweight detection method.

By Sejuti Basu, Ashima Sood, Vijay Kumar, Sahil Sharma
llmsdiffusioncomputer-vision
More like this →