Intermediateapplied

AI Safety & Ethics

Critical course on responsible AI use: deepfake and disinformation risks, prompt injection protection, data privacy in LLMs, algorithmic bias, regulations (EU AI Act, GDPR), corporate AI policy, and ethical decision-making frameworks.

4modules

10lessons

225 mintotal time

Anyone using AI in a professional contextaudience

Module 1

AI Risks & Threats

Taxonomy of AI risks: hallucinations, bias, misuse, data leaks, prompt injection, model poisoning, and supply chain attacks.

The AI Threat Landscape: What Can Go Wrong

Taxonomy of AI risks: hallucinations, bias, data leaks, prompt injection, model poisoning, and supply chain attacks.

20 min

Prompt Injection: How Attackers Hack AI

Direct and indirect prompt injection attacks, real-world examples, detection patterns, and mitigation strategies.

25 min

Deepfakes and Synthetic Media

Deepfake technology overview, detection tools, organizational policies, voice cloning scams, and the legal landscape.

20 min

Module 2

Report a bug

AI Safety & Ethics

AI Risks & Threats

Privacy & Data Protection

Bias & Fairness

Governance & Ethics