GTC Silicon Valley-2019: Machine Learning for Security and Security for Machine Learning
Note: This video may require joining the NVIDIA Developer Program or login
GTC Silicon Valley-2019 ID:S9805:Machine Learning for Security and Security for Machine Learning
Nicole Nichols(Pacific Northwest National Lab)
We discuss the connection between using machine learning for security applications as well as the security of machine learning algorithms. Examples include the use of NLP processing techniques with multi-layer RNNs for cyber event log anomaly detection. We compare the effectiveness of standard and bidirectional RNN language models for detecting malicious activity within the Los Alamos National Laboratory cybersecurity dataset. Additionally, deep learning augmentation of software fuzzing and light based adversarial attacks on deep learning image classification systems will be highlighted.