Today we’re joined by Nicole Nichols, a senior research scientist at the Pacific Northwest National Lab.
Subscribe: iTunes / Google Play / Spotify / RSS
Nicole joined me to discuss her recent presentation at GTC, which was titled “Machine Learning for Security, and Security for Machine Learning.” Our conversation explores the two use cases she presented, insider threat detection, and software fuzz testing. We discuss the effectiveness of standard and bidirectional RNN language models for detecting malicious activity within the Los Alamos National Laboratory cybersecurity dataset, the augmentation of software fuzzing techniques using deep learning, and light-based adversarial attacks on image classification systems. I’d love to hear your thoughts on these use cases!
Thanks to our Sponsor!
This week’s shows are drawn from some of the great conversations I had at the recent NVIDIA GPU Technology Conference, and they’re brought to you by Dell.
If you caught my tweets from GTC, you may already know that one of the announcements this year was a new reference architecture for Data Science Workstations, powered by high-end GPUs and accelerated software such as NVIDIA’s RAPIDS. Dell was among the key partners showcased during the launch, and offers a line of workstations designed for modern ML and AI workloads.
To learn more about Dell Precision workstations, and some of the ways they’re being used by customers in industries like Media and Entertainment, Engineering and Manufacturing, Healthcare and Life Sciences, Oil and Gas, and Financial services, visit Dellemc.com/Precision.
Mentioned in the Interview
- Paper: Recurrent Neural Network Language Models for Open Vocabulary Event-Level Cyber Anomaly Detection
- Paper: Deep Learning for Unsupervised Insider Threat Detection in Structured Cybersecurity Data Streams
- Paper: Faster Fuzzing: Reinitialization with Deep Neural Models
- Paper: Projecting Trouble: Light Based Adversarial Attacks on Deep Learning Classifiers
- Code: SafeKit
- Check out the rest of our GTC 2019 Series!
- Check out all of our great series from 2018 at the TWIML Presents: Series page!
- TWIML Online Meetup
- Register for the TWIML Newsletter
“More On That Later” by Lee Rosevere licensed under CC By 4.0