Summary of An Explainable Transformer-based Model For Phishing Email Detection: a Large Language Model Approach, by Mohammad Amaz Uddin and Iqbal H. Sarker
An Explainable Transformer-based Model for Phishing Email Detection: A Large Language Model Approach
by Mohammad Amaz Uddin, Iqbal H. Sarker
First submitted to arxiv on: 21 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
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 This research paper proposes an optimized transformer-based DistilBERT model for detecting phishing emails. The problem of phishing detection is a significant challenge in cybersecurity, with attackers using sophisticated methods to evade detection. Large Language Models (LLMs) and Masked Language Models (MLMs) have shown promise in addressing this issue. The authors fine-tune their DistilBERT model on a phishing email dataset, using preprocessing techniques to handle class imbalance issues. Experimental results demonstrate the model’s high accuracy in detecting phishing emails. Additionally, the paper applies Explainable-AI (XAI) techniques such as Local Interpretable Model-Agnostic Explanations (LIME) and Transformer Interpret to provide insights into the model’s decision-making process. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research helps keep our online accounts safe by creating a better way to detect fake emails. Phishing is when someone sends you an email that looks like it comes from a trustworthy source, but actually wants to trick you into giving away secrets or money. The bad guys are getting smarter at making these fake emails look real. To stop them, the researchers created a special computer model that can tell real emails apart from fake ones. They tested this model and found it was really good at spotting phishing attempts. They also figured out how to explain why their model made certain decisions, which is important for understanding how technology works. |
Keywords
* Artificial intelligence * Transformer
