Recent research and AI applications show that AI can cause unintentional harm to humans, such as making unreliable decisions in safety-critical scenarios. Thus, trustworthy AI has attracted immense attention recently, and this project place a strong emphasis on fairness,robustness and Privacy of the AI Inference Systems

Ongoing Work

• RVGuard:Certified Robustness for Trustworthy AI Inference Systems
  
• DPGuard:Differential Privacy techniques for Trustworthy AI Inference
  
• PPGuard:Privacy-Preserving Computation System for Deep Learning