# Fake News and Phishing Detection Using a Machine Learning Trained Expert System

arXiv: https://arxiv.org/abs/2108.08264 · HTML: https://mlsanity.com/paper/2108.08264/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 68 references that are in the map.
- First posted on arXiv 4 Aug 2021.

## Builds on (most cited first, 9 of 9)

- [Benchmarking Deep Reinforcement Learning for Continuous Control](https://mlsanity.com/paper/1604.06778/) (2016)
- ["Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detection](https://mlsanity.com/paper/1705.00648/) (2017)
- [Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss](https://mlsanity.com/paper/2002.04486/) (2020)
- [Federated Variance-Reduced Stochastic Gradient Descent with Robustness to Byzantine Attacks](https://mlsanity.com/paper/1912.12716/) (2019)
- [Estimating Continuous Distributions in Bayesian Classifiers](https://mlsanity.com/paper/1302.4964/) (2013)
- [Adaptively Truncating Backpropagation Through Time to Control Gradient Bias](https://mlsanity.com/paper/1905.07473/) (2019)
- [Towards Query-Efficient Black-Box Adversary with Zeroth-Order Natural Gradient Descent](https://mlsanity.com/paper/2002.07891/) (2020)
- [Sentimental LIAR: Extended Corpus and Deep Learning Models for Fake Claim Classification](https://mlsanity.com/paper/2009.01047/) (2020)
- [Expert System Gradient Descent Style Training: Development of a Defensible Artificial Intelligence Technique](https://mlsanity.com/paper/2103.04314/) (2021)

## Abstract (arXiv)

Expert systems have been used to enable computers to make recommendations and decisions. This paper presents the use of a machine learning trained expert system (MLES) for phishing site detection and fake news detection. Both topics share a similar goal: to design a rule-fact network that allows a computer to make explainable decisions like domain experts in each respective area. The phishing website detection study uses a MLES to detect potential phishing websites by analyzing site properties (like URL length and expiration time). The fake news detection study uses a MLES rule-fact network to gauge news story truthfulness based on factors such as emotion, the speaker's political affiliation status, and job. The two studies use different MLES network implementations, which are presented and compared herein. The fake news study utilized a more linear design while the phishing project utilized a more complex connection structure. Both networks' inputs are based on commonly available data sets.