Главная
Study mode:
on
1
Intro
2
A story we all know: Regular expressions
3
When's the last time you heard...?
4
Problem Statement: HTTP Proxy Logs
5
Machine Assisted Analysis
6
Two different types of machine learning
7
Supervised: Binary Classification
8
Classification With Random Forests
9
Generating synthetic abnormal data
10
Decision Trees
11
Unsupervised: Outlier Detection
12
Isolation Forests Liu, Ting, Zhao
13
A quick note about parameters
14
Classification With Isolation Forests
15
The beauty of scikit leam & python
16
Identifying Training & Test Data
17
Training, Testing & Evaluating a Model
18
Bonus: Most influential Features with
19
Analyzing Log Files
20
Bonus: Classifier Explanations with
21
Ideas for improvement
Description:
Explore machine learning techniques for analyzing Bro logs in this conference talk from Security Onion 2016. Dive into practical applications of cyborgism, focusing on HTTP proxy logs analysis. Learn about supervised and unsupervised machine learning approaches, including binary classification with random forests and outlier detection using isolation forests. Discover how to generate synthetic abnormal data, understand decision trees, and leverage scikit-learn and Python for efficient model training, testing, and evaluation. Gain insights into identifying influential features and interpreting classifier explanations. Acquire valuable ideas for improving log file analysis and enhancing cybersecurity practices through the integration of machine learning methodologies.

Practical Cyborgism - Machine Learning for Bro Logs

Security Onion
Add to list
00:00
-00:57