Explore how supercomputer-scale neural networks revolutionize defensive cybersecurity in this 35-minute Black Hat conference talk. Discover two groundbreaking applications of large neural networks: generating human-readable explanations of complex attacker behavior and detecting malicious activities with limited examples. Learn how to leverage publicly available models like OpenAI's GPT-3 for your own large-scale neural network experiments. Gain insights from speakers Younghoo Lee and Joshua Saxe as they demonstrate the transformative potential of these advanced models in enhancing security measures and expanding the horizons of machine learning applications in cybersecurity.
How Supercomputer-Scale Neural Network Models Apply to Defensive Cybersecurity Problems
Overview
Syllabus
How Supercomputer-scale Neural Network Models Apply to Defensive Cybersecurity Problems
Taught by
Black Hat
Related Courses
-
GPT-3 and Me - How Supercomputer-Scale Neural Network Models Apply to Defensive Cybersecurity Problems
-
Mem2Img - Memory-Resident Malware Detection via Convolution Neural Network
-
Deep Impact - Recognizing Unknown Malicious Activities from Zero Knowledge
-
Deep Neural Networks for Hackers - Methods, Applications, and Open Source Tools
-
DeepPhish - Simulating Malicious AI
-
The Cost of Learning from the Best - How Prior Knowledge Weakens the Security of Deep Neural Networks
