MCML

Explainable AI aims to improve the transparency of AI decisions through interpretable methods. We explore vulnerabilities in current explanation methods using adversarial attacks and develop intuitive visualizations to enhance user trust. Safe Image Generation focuses on developing algorithms to create unbiased and ethical images. We work on automatically identifying and eliminating harmful or biased outputs to ensure responsible AI usage. Machine Unlearning deals with the secure removal of specific data from AI models. Our research includes developing methods to comply with privacy regulations and provide transparent control of data. Knowledge Distillation transfers knowledge from large AI models to smaller, efficient versions. Our goal is to create lightweight models ideal for mobile and edge computing, ensuring high accuracy and robustness. BCI is a powerful way to understand users' perception directly by monitoring brain activities. We have been working on investigating effective BCI techniques using EEG and fNIRS for implicit monitoring of users' perception of given multimedia content. Here, perceptual dimensions include satisfaction, quality, immersiveness, emotion, sense of reality, etc. In particular, we focus on understanding perception for novel types of media such as 3D, high dynamic range (HDR), 4K UHD, etc. Furthermore, peripheral physiological signals such as skin temperature, skin conductance, and heart rate are also considered, which have potential to complement brain activities. Dynamic Vision Sensors detect rapid visual changes through event-based imaging. We research algorithms for efficient interpretation of DVS data, applicable to robotics, autonomous driving, and real-time monitoring due to their speed and efficiency. Often, heterogeneous sensors a