In War On Terrorism, New Cybersearch Tool Seeks Hidden Vulnerabilities
Researchers at the University at Buffalo’s School of Engineering and Applied Sciences have developed a prototype search engine designed to extract “hidden” information from public Web sites as part of an initiative to predict and stop potential terrorist activities.
The system, whose development is funded by the Federal Aviation Administration and the National Science Foundation, uses the Unintended Information Revelation (UIR) search method as its foundation.
Whereas existing search engines process individual documents according to the frequency with which a keyword appears in a single document, UIR looks for the optimal path linking a pair of seemingly unconnected concepts within numerous documents by building concept chain graphs, says UB computer science and engineering professor Rohini Srihari.
Malicious intentions may not be evident in a single document or Web site, but could be concealed within a multitude of documents and exposed via a concept chain graph. “The concept chains show you what may be of interest, but the real intelligence here is gleaned from looking for patterns of interest,” explains Srihari. “Once a pattern of interest is identified, then you can ask, ‘Are there more patterns like this?'”
The UB researchers developed the technique by using the chapters of the 9/11 Commission Report to set up ontologies.
The search tool may eventually improve public Web searches, helping biomedical researchers, for example, more effectively explore links between genes, proteins, and disease.
Abstracted by the National Law Enforcement and Corrections Technology Center(NLECTC) from the University at Buffalo Reporter (05/13/05); Goldbaum, Ellen .