It is my pleasure to announce that I have been invited to give a talk as an Early Career Researcher at Humboldt Colloquium in Toronto, which is going to take place from 2-4 Nov, 2012. Under the theme of “Excellence in Research”, I will present our work on Security Analysis of Social Bots on the Web at the Theoretical Sciences section of the colloquium’s interdisciplinary workshops.
The Early Career Researchers attending the colloquium are not members of the Humboldt Community but may wish to become fellows in the future. The researchers were selected for participation in the event by a committee of Humboldt alumni following on open call for papers under all science-related disciplines. More than 200 applications were received from researchers at all levels (students, PhDs, university/industry researchers), and only 25 applicants were accepted to present their current research at the workshops. Here’s a link to the preliminary program.
Starting next week, I’ll be joining Facebook (Menlo Park, CA) as a research intern. I’ll be working with the highly-qualified Site Integrity team under the kind management of Yuchun Tang . I will spend most of my time building a next-generation IP reputation and botnet detection system. I’m very excited about this opportunity and hope for a great experience!
This week, I will present our preliminary results on using machine learning to automatically detect malware at the poster session of the 21st Usenix Security Symposium, held in Bellevue, WA.
In this poster, we present Augur*: a large-scale machine learning system that uses malware static and dynamic analyses to predict the maliciousness of new files. Unlike other machine learning-based malware detection systems, Augur utilizes existing knowledge engineering performed by analysts and uses static and dynamic file properties (called Genes and Phenoms, respectively) as prominent predictive features. Augur can be deployed along side existing detection systems (e.g., an expert system) in order to achieve faster reactions to suspicious files at the endpoint, and to automatically generate effective signatures of new, unseen before malware.
Augur is the results of a successful collaboration between UBC and Sophos Inc. under MITACS Accelerate research internship program.
* An Augur was a priest and official in ancient Rome and Etruria. His main role was to interpret the will of the gods by studying the flight of birds.