📚︎Trustworthy and Responsible Artificial Intelligence

Explainable, interpretable, and verifiable AI

Robust machine learning and uncertainty quantification

AI safety, reliability, fairness, and accountability

Evaluation and benchmarking of intelligent systems

Responsible AI governance and risk management

📚︎Foundation Models and Autonomous AI Agents

Large language models and multimodal foundation models

Agentic AI, autonomous agents, and multi-agent systems

AI reasoning, planning, and tool-augmented intelligence

Human-AI collaboration and human-in-the-loop systems

Secure and controllable autonomous decision-making

📚︎AI Security and Privacy-Preserving Computing

Adversarial machine learning and robust AI defenses

Security and privacy of large language models and AI agents

Federated learning and privacy-preserving machine learning

Data poisoning, model extraction, and model integrity

AI-driven cyber threat detection and adaptive defense

📚︎Secure and Resilient Intelligent Systems

Edge intelligence, cloud-edge collaboration, and distributed AI

Internet of Things and cyber-physical system security

Digital twins and intelligent infrastructure

Resilient computing and dependable intelligent systems

Secure communications and distributed access control

📚︎AI-Enabled Digital Economy and Intelligent Decision-Making

Generative AI and digital business model innovation

AI-driven financial technology and fraud detection

Data-driven economic forecasting and intelligent decision support

Digital platform governance and algorithmic accountability

Digital transformation, economic resilience, and sustainability