Summary of Exploring the Efficacy Of Federated-continual Learning Nodes with Attention-based Classifier For Robust Web Phishing Detection: An Empirical Investigation, by Jesher Joshua M et al.
Exploring the Efficacy of Federated-Continual Learning Nodes with Attention-Based Classifier for Robust Web Phishing Detection: An Empirical Investigation
by Jesher Joshua M, Adhithya R, Sree Dananjay S, M Revathi
First submitted to arxiv on: 6 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed novel paradigm combines federated learning and continual learning to enable distributed nodes to continually update models on streams of new phishing data without accumulating data. This hybrid learning approach uses a custom attention-based classifier model with residual connections, tailored for web phishing detection. The model leverages attention mechanisms to capture intricate phishing patterns and achieves high accuracy, precision, recall, and f1-score. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Web phishing is a dynamic threat that requires detection systems to quickly adapt to the latest tactics. The proposed system uses federated learning and continual learning to enable distributed nodes to continually update models on new phishing data without accumulating data. This approach helps detect emerging phishing threats while retaining past knowledge, achieving high accuracy and precision. |
Keywords
» Artificial intelligence » Attention » Continual learning » F1 score » Federated learning » Precision » Recall
