
Security and Privacy in AI
Security and Privacy in AI is a comprehensive two-day course designed to equip participants with essential knowledge and skills to navigate the complex landscape of artificial intelligence security and privacy. This course addresses the growing need for professionals who can understand and mitigate the risks associated with AI systems while maximizing their potential benefits.
On the first day, participants delve into the fundamentals of AI security and privacy, exploring the value proposition of AI alongside its inherent risks. The course introduces key government and industry guidelines, including the NIST Artificial Intelligence Risk Management Framework, which provides a structured approach to identifying and managing AI-related risks. Participants also examine privacy considerations specific to AI systems and gain insights into the ISO/IEC CD 27090 guidance, which outlines security threats and potential failures in AI implementations. The second day focuses on practical aspects, covering attacks and defenses for Large Language Models (LLMs), AI observability techniques, secure coding practices tailored for AI development, and access control mechanisms for AI systems. By the end of the course, attendees will have developed a comprehensive understanding of AI security and privacy issues, enabling them to reason about potential risks and implement effective mitigation strategies in their organizations.
Course Duration
2 days
Audience
Security Professionals, Data Scientists/Engineers, AI/ML/MLOps/MLSecOps/DevOps/DevSecOps/SRE Staff, Devs, Managers
Prerequisites
Participants must have a computer capable of logging into a cloud lab system via ssh. Basic Linux command line skills and some coding experience are helpful but not required.
In the duration of this course, students will:
- Understand the value and risks that AI can bring to an organization
- List the primary government and industry guidance directed at security and privacy in AI
- Reason about the risks involved with AI and how to mitigate those risks
- Learn the types of attacks that can be made against AI models and mitigation techniques
Day 1
1. AI Security and Privacy Overview
2. NIST Artificial Intelligence Risk Management Framework
3. Privacy in AI Systems
4. ISO/IEC CD 27090 Guidance for security threats and failures in AI
Day 2
5. LLM Vulnerabilities and Mitigations
6. Observability for AI
7. Secure Coding Practices for AI
8. Access Control for AI
- Is there a discount available for current students?UMBC students and alumni, as well as students who have previously taken a public training course with UMBC Training Centers are eligible for a 10% discount, capped at $250. Please provide a copy of your UMBC student ID or an unofficial transcript or the name of the UMBC Training Centers course you have completed. Asynchronous courses are excluded from this offer.
- What is the cancellation and refund policy?Student will receive a refund of paid registration fees only if UMBC Training Centers receives a notice of cancellation at least 10 business days prior to the class start date for classes or the exam date for exams.
- What is Live Online training?Classes marked Live Online have the same content and expert instructors as our classroom training, but are delivered entirely online through our virtual classroom environment. Each class session is live, and led by an Instructor.