Presentations Our work in our own words
DEF CON 28 AI Village: Detecting hand-crafted social engineering emails with a bleeding-edge neural language model
Learning from Context: A Multi-view Deep Learning Architecture for Malware Detection
Machine learning (ML) used for static portable executable (PE) malware detection typically employs per-file numerical feature vector representations as input […]
Describing Malware via Tagging
Although powerful for conviction of malicious artifacts, machine learning based detection do not generally produce further information about the type […]
Scalable Infrastructure for Malware Labeling and Analysis
One of the best-known secrets of machine learning (ML) is that the most reliable way to get more accurate models […]
Hacking Facial Recognition Systems
Facial recognition is becoming ubiquitous, but how it works is often confused with standard image classification. In this short, high-level […]
Loss is More! Improving Malware Detectors by Learning Additional Tasks
Malware detection is perhaps the most common use case of machine learning for information security (ML-Sec/AI-Sec). ML-Sec malware detectors consist […]
Security data science – Getting the fundamental right
https://www.youtube.com/watch?v=XfT0Ju4vhvI&t=1254 A data science team is now table stakes for most security operations, however data science for security poses unique […]
Some Mistakes are More Mistaken Than Others: Using Cost-Matrix Clustering to Address Misclassification Cost Asymmetries in Website Content Classification
Website content classification has several salient characteristics as a machine learning problem, but perhaps the most salient is that it […]
Estimating Uncertainty for Binary Classifiers
In practical applications of binary classification, knowing the uncertainty of the prediction can be almost as important as knowing the […]