Karyn Benson Graduate Student Network telescopes are collections of unused but BGP-announced IP addresses. They collect the pollution of the Internet: scanning, misconfigurations, backscatter from DoS attacks, bugs, etc. For example, several historical studies used network telescopes to examine worm outbreaks. In this talk I will discuss phenomena that have recently induced many sources to send traffic to network telescopes. By examining this pollution we find a wealth of security-related data. Specifically, I'll touch on scanning trends, DoS attacks that leverage open DNS resolvers to overwhelm authoritative name servers, BitTorrent index poisoning attacks (which targeted torrents with China in their name), a byte order bug in Qihoo 360 (while updating, this security software sent acknowledgements to wrong IP addresses... for 5 years), and the consequence of an error in Sality's distributed hash table. Karyn recently defended her PhD in computer science. Prior to starting graduate school she wrote intrusion detection software for the US Army. When not looking at packets, Karb eats tacos, runs marathons, and collects state quarters. ... https://www.youtube.com/watch?v=UfI8LemMciE

Enjoy the videos and music you love, upload original content, and share it all with friends, family, and the world on YouTube. ... https://www.youtube.com/watch?v=QGs1ytSZ7sA

Black Hat USA 2017 ... https://www.youtube.com/watch?v=tEQHv1KBBkE

Anyone who keeps up with technology news has read about deep neural networks beating human champions at Go, achieving breakthrough accuracy at voice recognition, and generally driving today's major advances in artificial intelligence. Little has been said, however, about the ways deep neural network approaches are quietly achieving analogous breakthroughs in intrusion detection. My goal with this presentation is to change this, by demystifying deep neural network (deep learning) concepts, presenting research that shows that we can use deep learning methods to achieve breakthrough cyber-attack detection, and by introducing open source deep learning tools, so that attendees can leave equipped to start their own security deep neural network research. The presentation will start with an intuitive overview of deep neural networks, introducing the ideas that allow neural networks to learn from data and make accurate decisions about whether, for example, files are good or bad, or a given URL or domain name is malicious. After introducing deep neural networks, I'll go on to describe a case study: a deep neural network that uses a convolutional neural network approach to detect previously malicious URLs at higher accuracy than any previously reported techniques, which we have evaluated on live, real world data. Finally, I'll introduce the open source tools available for doing security deep learning research, giving attendees a starting place for incorporating deep neural networks into their own security practice. ... https://www.youtube.com/watch?v=W8FCN4YitWU