machine learning

Vern Paxson, University of California, Berkeley / Corelight, Inc. / International Computer Science Institute

Many of the most costly security compromises that enterprises suffer manifest as tiny trickles of behavior hidden within oceans of other site activity. This talk will examine the problem of developing robust detectors for particular forms of such activity. The process is in some ways a dual to that of adversaries who seek to design algorithms to identify users who employ particular approaches for keeping their network activity private.