RESEARCH 112
AI Security & Adversarial ML Lab
Securing AI systems research.
Research Focus
Research lab focused on AI security, adversarial attacks, and model protection.
Research Areas
Secure AI systems
Attack resilience
Model robustness
Methodology
Quantitative Analysis
Data-driven insights and statistical modeling.
Qualitative Research
In-depth interviews and user behavior studies.
Technologies & Methods
Adversarial TrainingModel HardeningRed Teaming
