Stanford AI Course Map 中文 GitHub ↗
← Back to the course map
Stanford · 2026—27 CS 253 ML Systems & Hardware —

Related course · ML Systems & Hardware

Securing AI Systems

中文:AI 系统安全

Model stealing, adversarial examples, data poisoning, and the LLM system attack surface.

Draft translation: official facts are checked; wording may change after native review.

3 units Spring 2027 Letter or Credit/No Credit —
AI Systems Security

Course positioning

Model stealing, adversarial examples, data poisoning, and the LLM system attack surface. This page keeps the official record and entry points; check the current syllabus for details.

What it covers

This is a related-course page: the official description below is the main content.

Prerequisites

See the official description (related courses do not have a separate prerequisite write-up).

Assessment & workload

Check the current syllabus.

Who it's for

Anyone interested in AI Systems Security.

Study advice

Read the official description and course site before deciding.

Related courses

Official course description

The explosive growth of AI systems has created new cybersecurity challenges. Systems that work well on benign prompts can be subverted with adversarial inputs that are easily disguised. The ensuing set of security problems gave rise to a new area of research, called AI security, that now spans thousands of research papers per year in multiple academic conferences. This course will introduce students to the key challenges of AI security, including modern approaches for securing computer systems that rely on AI models. The course content will evolve from year to year based on the latest research in the area.