Ken Liu is a Stanford CS PhD student and founder of The Open Anonymity Project, an initiative exploring privacy-preserving architectures for large language models.
His pioneering research sits at the intersection of language models and user privacy, with a focus on unlinkable inference — enabling users to query AI systems without revealing their identity or linking their requests.
Appearances
Key Contributions
- The Open Anonymity Project: Developing cryptographic and systems-level techniques (blind signatures, secure inference proxies) for private AI inference.
- Unlinkable Inference: Architectural work on decoupling user identity from LLM query patterns.