Main People Research Anonymity Privacy for Data Mining Sensor Network Security Publications Donggang's Matt's Nan's Classes	Research Areas Anonymous Communications Traffic analysis can expose a great deal about sensitive relationships; anonymous communications system are a promising technology to stop this kind of information leakage. We focus on ways to stop long-term attacks against these systems, as well as the application of anonymity to wireless and ad-hoc networks. Privacy-Preserving Data Mining Data mining extracts knowledge to support a variety of domains--marketing, weather forecasting, medical diagnosis, and national security--but it is still a challenge to mine certain kinds of data without violating the data owners' privacy. How to mine patients' private data, for example, is an ongoing problem in healthcare applications. The sticking point is how to protect privacy while preserving the usefulness of data mining results. Much research is under way to address obstacles, but practical privacy-preserving data mining systems are largely in the research and prototyping stages. Our goal in investigating privacy preservation issues is to take a systemic view of architectural requirements and design principles and explore possible solutions that would lead to guidelines for building practical privacy-preserving data mining systems. Security in sensor networks Wireless sensor networks have great potential, but they can be challenging to secure due to resource constraints and node compromise. Major topics include mechanisms for fundamental security protocols (e.g., key management and broadcast authentication), protection of critical sensor network services (e.g., routing, data management, localization, time synchronization, clustering), and the detection of replicant nodes. Intrusion and Malware Detection Hackers and malware writers pose a continuing threat to systems and networks. Many attacks can only be stopped by denying legitimate traffic, but attackers can be contained and then thwarted if they are detected early enough. We are investigating stepping-stone detection, a promising method of detecting hackers, and the propogation of worms and viruses, to understand how to detect new malware when there are no signatures for it. Incentives in Security and Privacy Most security problems are posed as black and white issues, but many times, models based on incentives are more approprate. In this work, we find areas in which incentives can be added to systems to enhance their security properties, and we use game-theoretic analysis to understand how incentives play out in existing systems. Research includes incentives for worm detection, anonymous communications, and digitial rights management.