We show that the time web sites take to respond to HTTP requests can leak private information, using two different types of attacks. The first, direct timing, directly measures re...
In the traditional setting, text categorization is formulated as a concept learning problem where each instance is a single isolated document. However, this perspective is not appr...
Traditional content-based e-mail spam filtering takes into account content of e-mail messages and apply machine learning techniques to infer patterns that discriminate spams from...
We introduce a novel mechanism for creating line drawings from three-dimensional models, which captures the dynamic nature of the drawing process. The approach takes into account ...
We present the machine learning framework that we are developing, in order to support explorative search for non-trivial linguistic configurations in low-density languages (langua...