Earn Your Business Degree, Tuition-Free, 100% Online!
Learn AI, Data Science & Business — Earn Certificates That Get You Hired
Overview
Google, IBM & Meta Certificates – 40% Off
One Coursera Plus subscription covers most Professional Certificates on Coursera.
Unlock All Certificates
This course explores building robust, resilient ML systems by addressing intentional adversary attacks and unintentional failures.
Syllabus
Introduction
- Machine learning security concerns
- How AI systems can fail and how to protect them
- Why AI security matters
- Attacks vs. unintentional failure modes
- ML security frameworks
- Security goals for ML: CIA
- Perturbation attacks and malicious input
- Poisoning attacks
- Reprogramming
- Physical domain: 3D adversarial objects
- Supply chain attacks
- Model inversion
- System manipulation
- Membership inference and model stealing
- Backdoors and existing exploits
- Reward hacking
- Side effects and misalignment
- Distributional shifts and incomplete testing
- Overfitting and underfitting
- Data bias considerations
- Effective techniques for building resilience in AI
- Threat modeling AI
- Dataset threat model
- Adversarial testing and red teaming
- API access and supporting components
- Supply chain
- Next steps in your AI security journey
Taught by
Diana Kelley