You are developing an anomaly-based IDS that employs artificial intelligence to categorize intrusion examples into various groups. Which of the following is the most intelligent approach to train the model? (Wentz QOTD)
A. Comprehensive knowledge base
B. Pre-selected features by subject matter experts
C. Ubiquitous deployment of sensors and agents
D. Layers of processing for feature transformation and extraction
Kindly be reminded that the suggested answer is for your reference only. It doesn’t matter whether you have the right or wrong answer. What really matters is your reasoning process and justifications.
My suggested answer is D. Layers of processing for feature transformation and extraction.
Wentz’s book, The Effective CISSP: Security and Risk Management, helps CISSP and CISM aspirants build a solid conceptual security model. It is a tutorial for information security and a supplement to the official study guides for the CISSP and CISM exams and an informative reference for security professionals.
IDS Detection Capability and Deployment
- A comprehensive knowledge base is more critical to signature-based or knowledge-based IDS instead of anomaly-based IDS.
- Ubiquitous deployment of sensors and agents is about IDS deployment, host-based or network-based.
- In normal cases, domain knowledge plays an important role in selecting features. However, it’s tiresome to do so manually when given hundreds of variables. That said, manual feature engineering, e.g., pre-selected features by subject matter experts, is tedious and impractical.
- Layers of processing for feature transformation and extraction imply an automated process of feature projection, e.g., Deep Learning.
Machine Learning and Deep Learning
- Neural Networks vs Deep Learning
- Deep Learning vs Neural Networks: Difference Between Deep Learning and Neural Networks
- 4 Types of Classification Tasks in Machine Learning
- Binary classification
- Supervised learning
- Machine Learning Tutorial: A Step-by-Step Guide for Beginners
- Feature selection
- How to Choose a Feature Selection Method For Machine Learning
- Feature Selection Techniques in Machine Learning
- Dimensionality reduction
- Feature (machine learning)
- The Art of Finding the Best Features for Machine Learning
- Discover Feature Engineering, How to Engineer Features and How to Get Good at It
- Some Key Machine Learning Definitions
- Part 1: Image Classification using Features Extracted by Transfer Learning in Keras
- How TensorFlow on Flink Works: Flink Advanced Tutorials
- Learning to Classify Text
- Applied Dimensionality Reduction — 3 Techniques using Python
- Feature Selection in Machine Learning
您正在開發一個基於異常的 IDS，它使用人工智能將入侵案例為不同的組別。 以下哪項是訓練模型的最智能方法？ (Wentz QOTD)
B. 主題專家預先選擇的特徵 (feature)