Thomas Yang
Founder of Phi Lab Foundation, leading the Foundation’s research program in AI security and trustworthy AI.
His research covers watermarking and provenance of model-generated content across text, image, audio, and DNA, detection of synthetic media, adversarial robustness, and red-teaming of foundation models, with broader interests in cybersecurity, model misuse and alignment, and information integrity. He directs the Foundation’s research agenda and external academic collaborations.
View profile →