Lets Talk

GenAl Security Research

Introducing Vision To The Fine-Tuning API
Developers Can Now Fine-Tune GPT-40 With Images And Text To Improve Vision Capabilities
Learn More
What an Incredible Evening at the Al x Security Summit!
On October 10th, 2024, I spent an incredible evening in Antler Singapore.
Learn More
S-tron China - S-Talent Talk
On September 20-21, 2024, I spent an unforgettable 2 days in S-tron China at the West Bund Art Center in Shanghai.
Learn More

Training a Automatic LLM RedTeaming Model

Why need LLM RedTeaming? LLMs are currently in a stage

Uninstall LLM safety alignment firewall! Perform surgery on LLM! Generate any desired content

Background In order to ensure that the content generated by

Use Jailbreaking to reverse the CoT process of ChatGPT o1-preview

Background Recently, OpenAI announced gpt-o1-preview and there are some interesting

Indirect Prompt Injection Vulnerability Google Colab AI

What’s Google Colab AI Natural language to code generation helps

Breaking Instruction Hierarchy in OpenAI's GPT-4o-mini

Background Have you seen the memes online where someone tells

Indirect Prompt Injection Vulnerability with AliBaBa TONGYI Lingma

What’s TONGYI Lingma TONGYI Lingma is an AI coding assistant,

Subscribe TrustAI Newsletter

Get our latest GenAI/LLM security research.

Join AISecX - AI Security Discord Community

Join the AISecX towards a secure Al era. We're building a safer future together, be part of it!

Join AISecX