Recently, several deep learning approaches have attempted to detect malware binaries using convolutional neural networks and stacked deep autoencoders. Although they’ve shown respectable performance on a large corpus of datasets, practical defense systems require precise detection during the malware outbreaks where only a handful of samples are available.

Sean Park (Trend Micro) demonstrates the effectiveness of the latent representations obtained through the adversarial autoencoder for malware outbreak detection. Using instruction sequence distribution mapped to a semantic latent vector, the model provides a highly effective neural signature that helps detecting variants of a previously identified malware within a campaign mutated with minor functional upgrade, function shuffling, or slightly modified obfuscations. Sean explains the effectiveness of generative adversarial autoencoders for static malware detection under outbreak situations where a single sample of a kind is available to detect similar in-the-wild samples. The model performance is evaluated over real-world macOS and Windows malware samples against traditional machine learning models.

Prerequisite knowledge

• A basic understanding of TensorFlow and malware

What you'll learn

• Discover the flexibility TensorFlow offers critical tools for cybersecurity against real-life malware threats
• Understand how deep neural networks can generate next-generation neural signatures effective against dynamically morphing malware
• Learn how neural signature changes the paradigm of cybersecurity