Ai-security

I also participated in the p4 ctf last weekend. I managed to solve two AI-related challenges, reminding me of the materials that I was doing during my undergraduate studies. There is also an interesting blind pwn challenge about fmt and uninitialized read vulnerability.

In this blog, I am going to share a brief summary of recent trending attack, prompts injection, on chatGPT, Sydney(Bing), or other LLM services.