Machine Learning for Security

<!--HTML--><p style="text-align: justify;">Applied statistics, aka &lsquo;Machine Learning&rsquo;, offers a wealth of techniques for answering security questions. It&rsquo;s a much hyped topic in the big data world, with many companies now providing machine learning as a service. This talk will demystify these techniques, explain the math, and demonstrate their application to security problems. The presentation will include how-to&rsquo;s on classifying malware, looking into encrypted tunnels, and finding botnets in DNS data.</p> <h4>About the speaker</h4> <p style="text-align: justify;">Josiah is a security researcher with <a href="http://www8.hp.com/us/en/software-solutions/dvlabs-security-threat-intelligence/" target="_blank">HP TippingPoint DVLabs</a>&nbsp;Research Group. He has over 15 years of professional software development experience. Josiah used to do AI, with work focused on graph theory, search, and deductive inference on large knowledge bases. As rules only get you so far, he moved from AI to using machine learning techniques identifying failure modes in email traffic. There followed digressions into clustered data storage and later integrated control systems. Current interests include clustering, classifying and understanding network traffic, often aimed at identifying malicious actors.</p>