BSidesLV 2017 has ended
Back To Schedule
Tuesday, July 25 • 14:30 - 15:25
Getting insight out of and back into deep neural networks

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
Deep learning has emerged as a powerful tool for classifying malicious software artifacts, however the generic black-box nature of these classifiers makes it difficult to evaluate their results, diagnose model failures, or effectively incorporate existing knowledge into them.  In particular, a single numerical output – either a binary label or a ‘maliciousness’ score – for some artifact doesn’t offer any insight as to what might be malicious about that artifact, or offer any starting point for further analysis.  This is particularly important when examining such artifacts as malicious HTML pages, which often have small portions of malicious content distributed among much larger amounts of completely benign content. 

In this applied talk, we present the LIME method developed by Ribeiro, Singh, and Guestrin, and show – with numerous demonstrations – how it can be adapted from the relatively straightforward domain of “explaining” text or image classifications to the much harder problem of supporting analysts in performing forensic analysis of malicious HTML documents.  In particular, we can not only identify features of the document that are critical to performance of the model (as in the original work), but also use this approach to identify key components of the document that the model “thinks” are likely to contain malicious elements.  This allows analysts to quickly assess both the validity of the model’s conclusion and rapidly identify regions that require additional inspection and evaluation.  In doing so the deep learning model is converted from a gnomic “black box” into a useful exploratory tool for malicious artifacts, even when the deep learning model itself may label the sample incorrectly. 

We complement this work by showing how knowledge extracted by this method – as well as existing expert knowledge – can be readily re-incorporated into deep learning models.


Richard Harang

Principal Data Scientist, Sophos
Richard Harang is a Principal Data Scientist at Sophos with over seven years of research experience at the intersection of computer security, machine learning, and privacy. Prior to joining Sophos, he served as a scientist at the U.S. Army Research Laboratory, where he led the research... Read More →

Tuesday July 25, 2017 14:30 - 15:25 PDT
Ground Truth (Firenze) 255 E Flamingo Rd, Las Vegas, NV 89169