AI/LLM red teaming, prompt injection, jailbreak research
AI Security
Hi folks, hope you are all doing great. Today, I would like to tackle BankGPT from the TryHackMe platform. Actually, it was my shortest article on Medium. Enjoy :) In order to understand the context embedded (whether model is context aware or not ) I pushed some mock up questions regarding to
AI Security
Hi everyone ! Today I would like to analyze an very interesting machine called Evil-GPT from TryHackMe. Let me start with why it sounds interesting ? Generally, we interact with LLM models directly in a web application format. However, in this scenario we are forced to interact with an LLM model managing
AI Security
“A practical walkthrough of the Certified AI/ML Pentester exam from being Rickrolled twice to learning that LLMs lie convincingly.” Hi everyone, hope you had magnificent holiday, in this article, I would like to share my C-AI/MLPen exam experience. From obstacles to technical details, I covered almost every hardships
AI Security
Hi fellows ! Hope you are great. In my subconscious, I have been considered how every AI text detection mechanism are detected. Somehow, in university life almost every course someone intends to create generative homeworks, papers or project via directly LLMs. In early days of LLMs, it is clear that everybody