How Hackers Jailbreak AI Chatbots
AI chatbots feel secure, until a hacker hides their true intent behind a layer of encoding.
This video is for educational and awareness purposes only.
▬▬ Tools Used ▬▬
– Kali Linux: Attacker machine
– Ubuntu Server: Victim
– LLM-powered chatbot (demo environment)
▬▬ ⏱️ Chapters ▬▬
00:00 Prologue
01:57 How AI Safety Filters Work
04:17 The Base64 Encoding Trick
05:49 Bypassing the Safety Filter
08:53 What Went Wrong & Prevention