01

Research Areas

🛡️

Safe Generative AI

Developing techniques to detect and defend against misuse of generative AI models, including deepfake detection, robust unlearning, and watermarking.

⚔️

Adversarial Machine Learning

Studying attack and defense strategies for machine learning models exposed to adversarial inputs during training and/or inference.

🤝

Secure Collaborative AI

Building robust, privacy-preserving collaborative/federated learning frameworks resilient to malicious attacks and data leakage.

⚖️

Multi-Agent Collaboration

Optimizing collaboration mechanism between agents in multi-agent systems based on large language models or multimodal foundation models

🔐

Learning on Encrypted Data

Enabling efficient inference and training directly on homomorphically encrypted data to preserve privacy throughout the ML pipeline.

🪪

Security of Biometric Systems

Investigating vulnerabilities in biometric recognition systems including presentation attack detection and template protection.

Past Research Topics

Information Fusion

Fair/Explainable AI

Anomaly Detection in Surveillance Videos