HE, Xinlei - HKUST Class Schedule & Quota

Class Schedule & Quota
2024-25 Fall 2023-24 Summer 2023-24 Spring 2021-22 Winter
2024-25 Fall
Common Core Course
The class information on this page will normally be updated every 15 to 20 minutes during class enrollment period.
» Student Information System (SIS)» PG Program/Course Catalog
Notes & Links
This service was first adapted from a student contribution in 2011-12 Fall. The efforts of all concerned are duly acknowledged.

AIAA AMAT BSBE CMAA DSAA EOAS FTEC FUNH INFH INTR IOTA IPEN LANG MICS PDEV PLED ROAS SEEN SMMG SOCH SYSH UCMP UCUG UFUG UGOD

COURSE INFO

VECTOR	[3-0-0:3]
DESCRIPTION	Nowadays, the integration of machine learning (ML) into various applications has brought unprecedented opportunities as well as challenges. Machine Learning Security and Privacy is a comprehensive course designed to address the critical need for understanding and mitigating the security and privacy risks inherent in ML systems. The course begins by examining foundational concepts in machine learning and its applications across different domains. It then delves into the specific vulnerabilities and threats that arise in ML systems, such as adversarial attacks, data poisoning, model inversion, and membership inference. Furthermore, the course emphasizes the ethical considerations surrounding ML security and privacy, including the impact of biased datasets, algorithmic fairness, and responsible AI practices. By the end of the course, students will have acquired a deep understanding of the security and privacy challenges in machine learning, along with practical skills to design, implement, and evaluate secure ML systems. This course equips students with essential knowledge to navigate the complex landscape of ML security and privacy effectively.

VECTOR

[3-0-0:3]

DESCRIPTION

Nowadays, the integration of machine learning (ML) into various applications has brought unprecedented opportunities as well as challenges. Machine Learning Security and Privacy is a comprehensive course designed to address the critical need for understanding and mitigating the security and privacy risks inherent in ML systems. The course begins by examining foundational concepts in machine learning and its applications across different domains. It then delves into the specific vulnerabilities and threats that arise in ML systems, such as adversarial attacks, data poisoning, model inversion, and membership inference. Furthermore, the course emphasizes the ethical considerations surrounding ML security and privacy, including the impact of biased datasets, algorithmic fairness, and responsible AI practices. By the end of the course, students will have acquired a deep understanding of the security and privacy challenges in machine learning, along with practical skills to design, implement, and evaluate secure ML systems. This course equips students with essential knowledge to navigate the complex landscape of ML security and privacy effectively.

DSAA 6000N - Machine Learning Security & Privacy (3 units)

Section	Date & Time	Room	Instructor	Quota	Enrol	Avail	Wait	Remarks
L01 (6074)	Tu 03:00PM - 05:50PM	Rm 202, W4	HE, Xinlei	30	17	13	0