About the Certificate
A specialized training program focusing on the current threat landscape related to the development of Artificial Intelligence. The curriculum covers both technical aspects of attacks on LLM models as well as operational and business risks arising from uncontrolled AI deployment in organizations.
Skills Acquired
- AI Model Attacks: Understanding model manipulation techniques, including jailbreaking and risks associated with Agentic AI systems.
- Deployment Security: Identifying "Shadow AI" issues (unauthorized AI usage) and awareness of data leakage risks through model prompting.
- Social Engineering 2.0: Analyzing the evolution of AI-powered phishing and new user manipulation methods.
- Risk Management: Recognizing unpredictable deployment costs and risks stemming from excessive autonomy granted to AI systems.
- Incident Analysis: Case-study analysis of real-world security failures involving AI technology.