If you would like to participate in research, below are some of my ongoing research projects. You can participate at different levels:
Intruders may circumvent the primary security barriers and gain unauthorized access to a system; intrusion detection provides the second line of defense. Based on past access history, we seek to build models that characterize normal behavior. Historical data can be at the packet/connection, system call, or user command level. Behavior that deviates from these models is considered a potential intrusion.
We investigate machine learning techniques for detecting any unusual functioning of a space shuttle component, such as a fuel valve. Machine learning techniques are especially useful to generate detection knowledge from historical data. During the monitoring process, behavior that significantly deviates from the learned model could indicate potential problems.
The main goal of this project is to develop novel techniques for a more adaptive and personalized web. Personalized techniques cater to specific users and adaptive methods learn from the users' (potentially changing) behavior. Rather than requesting the user to provide his/her interests, we propose modeling user interests non-intrusively (no direct user involvement) based on access behavior. The user models can then be used to assist tasks like information searching, web navigation, and electronic commerce.
Client-server programs are becoming more prevalent as the Internet grows. To ease the burden of repeatedly writing low-level communication and protocol code, we seek to design a simple language that specifies the desired communication and protocol features, and construct a generator that produces the corresponding skeletons and stubs. The programmer then supplies the rest of the application-specific code. Besides saving development time, our approach also reduces programming errors.
The above application areas present fundamental issues in machine learning and data mining: scalability, skewed distributions, non-uniform cost, adaptability, knowledge sharing, pruning...