Welcome to the forum for Trung’s AI security and alignment research group! This is our space to discuss ideas, share progress, and collaborate on projects.
How this forum works:
Each topic = a project. We create a dedicated topic for each research project (e.g., “Watermark Robustness”). Post your ideas, questions, findings, and discussion within the relevant project topic.
Set up your profile — add your name and research interests to your profile so others know what you’re working on.
Browse active projects in the latest discussions and jump into anything that interests you.
Contributing is easy — share a paper you found relevant, ask a question, propose an experiment, or give feedback on someone’s idea. Use 
to signal agreement or appreciation.
Questions or suggestions about the forum itself? Post in Site Feedback or contact the admins.