My name is Jiarui Li. I work at the intersection of AI security, applied cryptography, and practical systems, with a focus on LLM privacy and trustworthy AI.
This blog is where I turn reading and prototyping into structured notes—problem definitions, threat models, techniques, and what I think still doesn’t work.
Topics I write about
- Prompt privacy & semantic leakage in LLM applications
- Threat modeling for enterprise LLM deployments
- Secure inference / privacy-preserving ML systems
- Integrity in federated learning