Secure and Reliable Infrastructure for LLM-powered AI Agents

· 1 min read

Our research systematically enhances AI agents with adversarial robustness, operational reliability, data privacy, and verifiability. By embedding deterministic guarantees into inherently unstable AI agent systems, our infrastructure empowers the large-scale industrial adoption of AI agent applications.

Representative References

  1. BlockA2A: Towards Secure and Verifiable Agent-to-Agent Interoperability , 2025.
  2. Agentic Privacy-Preserving Machine Learning , 2025.
  3. Anonymization-Enhanced Privacy Protection for Mobile GUI Agents: Available but Invisible , 2026.
  4. Blind Gods and Broken Screens: Architecting a Secure, Intent-Centric Mobile Agent Operating System , 2026.
Zhuotao Liu
Authors
Zhuotao Liu
Associate Professor