Summary of Evaluating Ml-based Anomaly Detection Across Datasets Of Varied Integrity: a Case Study, by Adrian Pekar and Richard Jozsa
Evaluating ML-Based Anomaly Detection Across Datasets of Varied Integrity: A Case Study
by Adrian Pekar, Richard Jozsa
First submitted to arxiv on: 30 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Networking and Internet Architecture (cs.NI)
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 paper addresses a critical issue in cybersecurity: detecting anomalies in network traffic flows. The authors focus on the integrity of datasets used to develop machine learning models for anomaly detection. They introduce two refined versions of the CICIDS-2017 dataset, NFS-2023-nTE and NFS-2023-TE, which are processed using NFStream to ensure methodological soundness. The study compares the performance of the Random Forest algorithm across different datasets, including original CICIDS-2017, WTMC-2021, CRiSIS-2022, and the refined counterparts. The results show that the RF model is robust and achieves consistent high-performance metrics regardless of dataset quality. This study highlights the importance of refining and improving dataset generation for network security research. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps keep the internet safe by making sure the data used to detect cyber threats is accurate. It’s like checking a recipe book to make sure all the ingredients are correct before making cookies. The authors created two new versions of an existing dataset, called NFS-2023-nTE and NFS-2023-TE, which are better than the original one. They then tested how well a special computer program, called Random Forest, could detect anomalies in different datasets. Surprisingly, this program worked really well, even with imperfect data. This study shows that making sure our data is accurate is important for keeping the internet safe. |
Keywords
* Artificial intelligence * Anomaly detection * Machine learning * Random forest
