課程說明
資安問題與挑戰。監督式與非監督式學習。分類與回歸演算法。資安領域之效能評估。處理不平衡領域之技術。異常偵測。主動學習策略。資料串流之資安。機器學習脆弱性。資安領域之 NLP。惡意程式、入侵、信用卡詐欺偵測、網路釣魚、認證濫用防範。
先修條件
- 先修條件：本課程無正式先修條件。但學生應具備對人工智慧、機器學習之合理基礎接觸，並有以高階語言之程式設計經驗。
條件與方式
- 先修條件：本課程無正式先修條件。但學生應具備對人工智慧、機器學習之合理基礎接觸，並有以高階語言之程式設計經驗。
原文參考文本
Cybersecurity problems and challenges. Supervised and unsupervised learning. Classification and regression algorithms. Performance assessment in cybersecurity domains. Techniques for imbalanced domains. Anomaly detection. Active learning strategies. Cybersecurity of data streams. ML vulnerability. NLP for cybersecurity. Malware, intrusion, credit card fraud detection, phishing, authentication abuse prevention.
- Prerequisite(s): There are no official prerequisites for this course. However, students should have reasonable exposure to Artificial Intelligence, Machine Learning, and some programming experience in a high-level language.
來源與參考
保留日期與來源以協助你核實資料。為便於閱讀提供譯文；官方來源為條件與要求的參照。
來源參考 : https://calendar.carleton.ca/grad/courses/COMP/