Richard Harang, Author at Sophos AI

Introduction The machine learning-based detection technologies we build at Sophos AI rely on many information sources, including binary programs, system […]

Gift cards are a favorite way for scammers to squeeze money out of their victims. Unlike wire or bank transfers, […]

The Sophos AI team is excited to announce the release of SOREL-20M (Sophos-ReversingLabs – 20 million) – a production-scale dataset […]

So, you’ve followed the advice in Part 1 of this series. Now you’ve got a nice big data set and you’re pretty sure that […]

Introduction When we move machine learning models from the lab to the real world, tracking and evaluating model performance becomes […]

Attention conservation notice: This is a slightly expanded version of a Twitter thread I posted back in January 2020. If […]

Author Richard Harang

A machine learning approach to inferring the maliciousness of unknown IP addresses, autonomous systems, and ISPs

How SophosAI Stops BEC gift card scams

Sophos-ReversingLabs (SOREL) 20 Million sample malware dataset

ML Expectation vs. Reality, Part 2: Doing the Actual Analysis

How much malware is out there, anyway?

Debugging Deep Learning Models

Malware Data Science: Attack Detection and Attribution

De-anonymizing programmers via code stylometry

Crafting adversarial input sequences for recurrent neural networks

Git blame who?: Stylistic authorship attribution of small, incomplete source code fragments