Presented at
Black Hat USA 2015,
Aug. 6, 2015, 11 a.m.
(50 minutes).
Machine learning is rapidly gaining popularity in the security space. Many vendors and security professionals are touting this new technology as the ultimate malware defense. While evidence from both research and practice validates the improved efficacy of machine learning-based approaches, their drawbacks are rarely discussed.
In this talk, we will demonstrate, from an attacker's perspective, how commonly deployed machine learning defenses can be defeated. We then step back and examine how existing systemic issues in the network security industry allow this to occur, and begin the discussion with the community about these issues. Finally, we propose a solution that uses novel data sourcing techniques to address these problems.
Presenters:
-
Bob Klein
- BluVector
Bob Klein is a machine learning specialist and software engineer on the BluVector Cyber Intelligence Platform. He is actively involved in researching next generation machine learning approaches to combat emerging malware threats. He received his Bachelor's Degree in Mechanical and Aerospace Engineering from Princeton University and his Master's Degree in Aeronautics and Astronautics from MIT, where he studied both supervised and unsupervised machine learning algorithms. Bob is a National Science Foundation Graduate Research Fellow and a recipient of the Kerrebrock Fellowship in Aeronautics and Astronautics.
-
Ryan Peters
- BluVector
Ryan Peters is currently a software engineer on the BluVector Cyber Intelligence Platform. He is actively involved in researching next generation machine learning approaches to combat emerging malware threats. He holds a Bachelors of Science in Biomedical Engineering from Case Western Reserve University and a Masters of Science in Biomedical Engineering from Duke University with a focus on computational modeling.
Links:
Similar Presentations: