Monthly Meetup

We'll be meeting at the Terbium Labs offices in the Federal Hill neighborhood of downtown Baltimore, Maryland. There will be pizza!

We'll be having two talks this time, one on Russian Propaganda and one on building datasets.

Your Facts Are Not Safe with Us: Russian Information Operations as Social Engineering by Meagan Dunham Keim: Over the past few years, Russia has proven itself to be an undeniable master of information operations. The techniques vary, but the majority of them focus on creating new realities and subverting Western values. This makes response efforts much more challenging, and Russia’s info ops strategies have become a key part of the arsenal the country draws upon in achieving its aims both at home and abroad.

By describing personal experience with a steady diet of state-sponsored propaganda while studying abroad in Russia, and by examining the country’s annexation of the Ukrainian peninsula of Crimea as a case study, I will give you an in-depth look at Russia’s info ops and why they’re so effective. I will explain why it’s useful to frame Russian information operations as large-scale social engineering and the implications that has for mitigating the security problems involved.

Building a Benign Dataset by Robert Brandon and John Seymour: Though featurization is important, the datasets used to make conclusions are just as important, if not more so. Information Security researchers often cannot release data, resulting in lack of benchmark datasets and causing cross-dataset generalization to be understudied in this domain. Despite this fact, presence of dataset bias (especially negative set bias) is now common knowledge in machine learning for malware classification. For these reasons, we have developed a standard for benign datasets to be used toward machine learning in the malware classification domain. We are also releasing a sample benign data set designed to minimize these problems.