Workshop
AI Red Teaming: Breaking LLMs
Attack the AI itself. Learn prompt injection, jailbreaking, data poisoning, and model extraction — the hottest new frontier in offensive security.
- Certificate of completion
- Taught by Harminder Singh · since 2015
- 4.8★ · 121 Google reviews
advanced12+ hours2-day workshop
What you'll learn
- Prompt injection — bypassing safety guards
- Jailbreaking techniques & taxonomy
- Data poisoning & backdoor attacks
- Model extraction & inversion
- Adversarial examples against vision models
- LLM-powered red team automation
- Responsible disclosure & AI safety
What's included
- 12+ hours of hands-on training
- Live AI demos & tools
- Certificate of completion
- AI toolkit access
- WhatsApp community access
Workshops are conducted in your college. Check with your TPO.