Vulnerabilities in AI Agents
LLMs are becoming increasingly accessible to everyone. It is very easy to create your own LLM system, however like with any new technology, they are challenging to secure. Many AI systems are vulnerable [...]
BloreBank ChatBot – Introducing our Prompt Injection Game
BloreBank Chatbot is a prompt injection game where you try to trick the AI into giving away sensitive information. With 10 levels, each one adds new safeguards against these tricks, making it tougher [...]
Guiding Secure AI: NCSC’s Framework for AI System Security
The introduction of the newly released guidelines for secure AI system development by the National Cyber Security Centre (NCSC) emphasizes the growing importance and integration of AI systems in various sectors. It acknowledges [...]
Unravelling the Web: AI’s Tangled Web of Prompt Injection Woes
Ah, the marvels of technology – where Artificial Intelligence (AI) emerges as the golden child, promising solutions to problems we didn't know we had. It's like having a sleek robot assistant, always ready [...]