University of Cambridge > Talks.cam > Computer Laboratory NetOS Group Talklets > Mining Large-Scale Internet Data to Find Stealthy Abuse

Mining Large-Scale Internet Data to Find Stealthy Abuse

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Gemma Gordon.

This is a full talk NOT a talklet.

Internet abuse is advancing to a hard-to-detect stealthy space. A number of factors contribute to this shift: increasing sophistication of adversaries in response to maturing Internet defenses, new powerful adversaries (such as nation-state actors) surfacing, and the emergence of an underground economy that facilitates access to the tools and resources required to conduct attacks. Further, the shift towards high-speed networks plays to the advantage of abusers, producing data of a nature and scale that serves as another obfuscation layer for their abuse operations. From defenders’ point of view, the detection task is hard: the threat signal is often buried inside a sea of benign data. In this talk, I will discuss my work on deriving actionable security intelligence from hundreds of millions of log records. I will begin with an overview on Internet abuse research and will discuss in depth my work on two detection problems: (i) detecting large-scale coordinated and stealthy attacks, and (ii) mining network traffic to find surreptitious forms of online tracking.

Bio: Mobin Javed is a Post-doctoral Research Scholar in the Networking and Security group at the International Computer Science Institute, Berkeley. She received her Ph.D. from UC Berkeley in 2016 advised by Vern Paxson, and will be joining LUMS as an Assistant Professor in Spring 2018. Her research focuses on analyzing real-world data from large-scale networked systems to understand Internet adversaries, and to develop practically deployable solutions for fighting cyber threats. Some of her projects include: (i) detection of stealthy and coordinated attacks, (ii) measurement of surreptitious tracking, and (iii) measurement and evasion of Internet censorship. Her work on detecting credential spear-phishing attacks is the winner of the 2017 Internet Defense Prize. She also has a keen interest in social impact, and was recently selected as a fellow at the Data Science for Social Good (DSSG) program at the University of Chicago, where she worked with the government of Mexico to help fight poverty through data science. Mobin is also the co-founder of GradApp Lab, Pakistan, a mentoring effort that connects aspiring grad school applicants with mentors abroad.

This talk is part of the Computer Laboratory NetOS Group Talklets series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity