Loading…
FloCon 2019 has ended
Tuesday, January 8 • 9:30am - 10:00am
Improved Hunt Seeding with Specific Anomaly Scoring

Sign up or log in to save this to your schedule and see who's attending!

Feedback form is now closed.
As the practice of hunting has spread through enterprise cyber security, interest in generalized anomaly detectors to seed hunts has also increased. The generally accepted premise seems to be that security events are rare and rare events are almost always anomalous. Therefore, if one seeds hunts with anomalous events, then the hunts are more likely to uncover activity of interest. However, implementing directed hunts in this manner requires the ability to define and detect anomalous behavior within complex systems. This is typically done probabilistically and there are several products available that employ machine learning approaches, such as neural networks, to define anomalous network activity. However, unsupervised learning approaches are inescapably plagued by high false alarm rates which, in turn, lead to analyst alert fatigue. To decrease false alarm rates, one may tune such products to only alert in cases of extremely anomalous events. But this still fails to address the heart of the problem which is that generalized anomaly detection for an entire network is probably not an optimal approach. Rather, defenders should develop a number of specific models. What is required is a scalable and repeatable framework for doing so. We present an open source approach for cyber security experts and data scientists/statistical engineers to collaboratively develop specific anomaly scoring models. Our approach utilizes a non-parametric kernel density estimator to evaluate the distributions of security logs. Once the desired distribution has been learned, analysts may use it to score records with a single-number, probabilistic measure of anomalousness. Logs can then be filtered based on this anomalousness score and rare events can be utilized to seed hunts. After sufficient validation, models may be transitioned to detectors which alert defenders when some criterion is met.

Attendees will Learn:
Attendees will be presented with a flexible, open source tool for non-parametrically modeling multivariate densities of network logs. Once constructed, such models can be utilized to score the anomalousness of log records and facilitate directed hunting. More subtly, attendees will gain insight into the potential benefits available through iteratively collaborating with statistical engineers/data scientists, such as the construction of highly customizable models for specific phenomena on specific networks.

Speakers
avatar for Brenden Bishop

Brenden Bishop

Data Scientist, Columbus Collaboratory
Brenden Bishop is a data scientist at Columbus Collaboratory. He focuses on developing prototype solutions for network defenders and enterprise IT in a variety of problem areas, including network anomaly detection and active directory tidying. He is a graduate of The Ohio State University... Read More →



Tuesday January 8, 2019 9:30am - 10:00am
Grand Ballroom 300 Bourbon St, New Orleans, LA 70130

Attendees (23)