Summary of Anomaly Detection in Okta Logs Using Autoencoders, by Jericho Cain et al.
Anomaly Detection in OKTA Logs using Autoencoders
by Jericho Cain, Hayden Beadles, Karthik Venkatesan
First submitted to arxiv on: 11 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: 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 The paper proposes an innovative approach to detecting cybersecurity events using unsupervised techniques, specifically autoencoders, to address limitations in traditional rule-based models. By transforming and simplifying log data from users, the authors aim to improve retrospective analysis, adaptability, and reduce false positives. The method is evaluated on the output of the transformed and filtered data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper tries to solve a problem with how cybersecurity events are detected using special computer programs. Right now, these programs use rules that can’t look back very far in time or have a set list of rules. This makes it hard to analyze past events or deal with new situations. To fix this, the authors suggest using a type of AI called an autoencoder. They take the complex data from users and make it simpler so the autoencoder can understand it better. Then they see how well the method works. |
Keywords
» Artificial intelligence » Autoencoder » Unsupervised
