1. Erik Jonsson School of Engineering and Computer Science The University of Texas at Dallas Cyber Security Research on Engineering Solutions Dr. Bhavani Thuraisingham Director, CyberSecurity Research Center Erik Jonsson School of Engineering and Computer Science The University of Texas at Dallas January 30, 2006

2. Erik Jonsson School of Engineering and Computer Science Cyber Security/Information Assurance Research Areas  Network Security Secure wireless and sensor networks  Systems and Language Security Embedded systems security, Buffer overflow defense  Data and Applications Security Secure web services, Semantic Grids, Privacy  Intrusion Detection Data mining techniques for intrusion detection  Security Theory and Protocols Secure group communication  Security Engineering Secure component-based software  Cross Cutting Themes Vulnerability analysis, Access control

3. Erik Jonsson School of Engineering and Computer Science Data and Applications Security Research  Secure Data Sharing Across Coalitions Organizations share data and yet maintain theory autonomy and enforce policies  National Security and Privacy Privacy-preserving data mining and surveillance techniques  Dependable Semantic Webs Next generation semantic web technologies with security and trust management  Secure Geospatial/Multimedia Information Systems Authorization Models for Image and Video systems

4. Erik Jonsson School of Engineering and Computer Science Secure Data Sharing among Coalitions: Export Data/Policy Component Data/Policy for Agency A Data/Policy for Coalition Export Data/Policy Component Data/Policy for Agency C Component Data/Policy for Agency B Export Data/Policy

5. Erik Jonsson School of Engineering and Computer Science Privacy Preserving Data Mining: Data Mining causes Privacy Violations Randomization –Introduce random values into the data and/or results –Challenge is to introduce random values without significantly affecting the data mining results Privacy preserving link analysis

6. Erik Jonsson School of Engineering and Computer Science Secure Semantic Web: Confidentiality, Privacy and Trust Policies Ontologies Rules Semantic Web Engine XML, RDF Documents Web Pages, Databases Inference Engine/ Rules Processor Interface to the Semantic Web Technology Being developed at UTD

7. Erik Jonsson School of Engineering and Computer Science Determine normal events Determine suspicious events Analyze video and image data and determine whether events are suspicious Suspicious Event Detection

8. Erik Jonsson School of Engineering and Computer Science Suspicious Event Detection We define an event representation measure based on low-level features Having a well-defined event representation allows us to compare events. Our desired effect is that video events that contain the same semantic content will have small dissimilarity from one another (i.e. be perceived as the same event). This allows us to define “normal” and “suspicious” behavior and classify events in unlabeled video sequences appropriately A visualization tool can then be used to enable more efficient browsing of video data

9. Erik Jonsson School of Engineering and Computer Science Social Network Analysis Suspicious Message Detection –Adaptation of existing spam detection techniques Naïve Bayesian Classification Support Vector Machines Keyword Identification Detecting chains of conversation through message correlation analysis –Determination of word frequencies within a message –Comparison between existing suspicious messages

10. Erik Jonsson School of Engineering and Computer Science ? Financial Aid Information (P3) Office of admission (P1) VIP web page (P2) What page is Next?? Web Page Prediction

11. Erik Jonsson School of Engineering and Computer Science Images Segments Blobs Automatically annotate images then retrieve based on the textual annotations. Image Annotation and Extraction

12. Erik Jonsson School of Engineering and Computer Science Geospatial Data Integration

13. Erik Jonsson School of Engineering and Computer Science Dependable Information Management Many DoD and DoE systems have to meet timing constraints Sensor/Stream data has to be processed within a certain time and sent to the war fighter Security and real-time processing may be conflicting requirements Need flexible policies

14. Erik Jonsson School of Engineering and Computer Science In Conclusion We need to develop infrastructures middleware and applications that are end-to-end secure We need confidentiality, privacy, trust, integrity, fault tolerance and real0time processing Flexible policies are critical Need Risk-based access control