AI Hacking Workshop

Understanding Adversarial Prompting & Exploitation Techniques in AI Systems

📍 In-Person · Mumbai | 💻 Bring Your Laptop - Live Exercises Included

AI systems are only as secure as the prompts they trust. In this hands-on workshop, we pull back the curtain on the techniques attackers use to manipulate, deceive, and break large language models - and what you can actually do about it.

What You'll Learn & Practice:

01 - Anatomy of Prompt Injection Attacks: Understand how crafted inputs hijack AI instructions and override system behaviour in real-world deployments.

02 - Jailbreaking Techniques in the Wild: Explore the most effective methods used to bypass constraints in modern AI systems.

03 - Real-World Risk Scenarios: Walk through concrete attack cases that show how adversarial prompting translates to tangible business and security risk.

04 - Building Stronger AI Defences: Leave with actionable strategies for hardening AI systems — from input validation to architectural safeguards.

05 - Live Exercises - Bring Your Laptop: This isn't just theory. You'll actively attempt prompt injection and jailbreaking attacks in a controlled environment, guided step by step.

Come ready to hack - your laptop is your tool for the day.

Ideal for security professionals, AI developers, and anyone building with or around LLMs.