Younghoo Lee

Principal Data Scientist

AI LLM Machine Learning Malware spam

Younghoo is a Principal Data Scientist at Sophos AI. He is dedicated to researching and developing machine learning models to detect malicious emails, binaries, and categorize web content. He also employs Large Language Models (LLMs) to improve automation within Security Operations. He has shared his insights on ML topics at Black Hat, RSA and Virus Bulletin. Prior to joining Sophos, he contributed to malware classification systems at Symantec and worked on mobile software platforms at Samsung Electronics. Outside of his work, Younghoo delights in discovering bushwalking trails around Sydney.

@younghoo_au

Introduction The use of deep neural networks has significantly improved the performance of machine learning in fields such as image […]

Introduction Many organizations are transitioning their security management to the cloud, where it is much easier to collect and access […]

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

GPT is a powerful text generation model, but its text generation is unconstrained. This session will discuss how to control GPT to produce sentences which meet specific style or content requirements. The session will review approaches that allow attendees to drive GTP to write SPAM and HAM messages and will demonstrate how to convert GPT into a SPAM filter which detects the generated SPAM.

Generative artificial intelligence technologies such as OpenAI’s ChatGPT and DALL-E have created a great deal of disruption across much of our digital lives. Creating credible text, images and even audio, these AI tools can be used for both good and ill. That includes their application in the cybersecurity space.

Targeted phishing emails are a major cyber threat on the Internet today and are insufficiently addressed by current defenses. In this paper, we leverage industrial-scale datasets from Sophos cloud email security service, which defends tens of millions of customer mailboxes, to propose a novel Transformer-based architecture for detecting targeted phishing emails. Our model leverages both natural language and email header inputs, is more computationally efficient than competing transformer approaches, and we show that it is less prone to adversarial attacks which deliberately replace keywords with typos or synonyms.

Younghoo Lee

Blog Posts

GPT-3 and Cybersecurity

A Natural Language Query Interface for XDR/SQL

How SophosAI Stops BEC gift card scams

Presentations

Black Hat 2022: GPT-3 and Me: How Supercomputer-scale Neural Network Models Apply to Defensive Cybersecurity Problems

BSides LV 2022: GPT-3 and Me: How Supercomputer-Scale Neural Network Models Apply to Defensive Cybersecurity Problems

AI vs AI: Creating Novel Spam and Catching it with Text Generating AI

Publications

The Dark Side of AI: Large-Scale Scam Campaigns Made Possible by Generative AI

CatBERT: Context-Aware Tiny BERT for Detecting Targeted Social Engineering Emails

SeqDroid: Obfuscated Android Malware Detection Using Stacked Convolutional and Recurrent Neural Networks