# Activation Analysis of a Byte-Based Deep Neural Network for Malware Classification

arXiv: https://arxiv.org/abs/1903.04717 · HTML: https://mlsanity.com/paper/1903.04717/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Mar 2019.

## Built on by (most cited first, 14 of 14)

- [Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art](https://mlsanity.com/paper/2112.12310/) (2021)
- [Detection of out-of-distribution samples using binary neuron activation patterns](https://mlsanity.com/paper/2212.14268/) (2022)
- [AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples](https://mlsanity.com/paper/2404.19460/) (2024)
- [Transformers for End-to-End InfoSec Tasks: A Feasibility Study](https://mlsanity.com/paper/2212.02666/) (2022)
- [Mal2GCN: A Robust Malware Detection Approach Using Deep Graph Convolutional Networks With Non-Negative Weights](https://mlsanity.com/paper/2108.12473/) (2021)
- [Evaluating Ensemble and Deep Learning Models for Static Malware Detection with Dimensionality Reduction Using the EMBER Dataset](https://mlsanity.com/paper/2507.16952/) (2025)
- [Echelon: Two-Tier Malware Detection for Raw Executables to Reduce False Alarms](https://mlsanity.com/paper/2101.01015/) (2021)
- [On deceiving malware classification with section injection](https://mlsanity.com/paper/2208.06092/) (2022)
- [Artificial Intelligence for Cybersecurity: Threats, Attacks and Mitigation](https://mlsanity.com/paper/2209.13454/) (2022)
- [Empirical Quantification of Spurious Correlations in Malware Detection](https://mlsanity.com/paper/2506.09662/) (2025)
- [A Comparison of State-of-the-Art Techniques for Generating Adversarial Malware Binaries](https://mlsanity.com/paper/2111.11487/) (2021)
- [Instance Attack:An Explanation-based Vulnerability Analysis Framework Against DNNs for Malware Detection](https://mlsanity.com/paper/2209.02453/) (2022)
- [High-resolution Image-based Malware Classification using Multiple Instance Learning](https://mlsanity.com/paper/2311.12760/) (2023)
- [EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability](https://mlsanity.com/paper/2607.24177/) (2026)

## Abstract (arXiv)

Feature engineering is one of the most costly aspects of developing effective machine learning models, and that cost is even greater in specialized problem domains, like malware classification, where expert skills are necessary to identify useful features. Recent work, however, has shown that deep learning models can be used to automatically learn feature representations directly from the raw, unstructured bytes of the binaries themselves. In this paper, we explore what these models are learning about malware. To do so, we examine the learned features at multiple levels of resolution, from individual byte embeddings to end-to-end analysis of the model. At each step, we connect these byte-oriented activations to their original semantics through parsing and disassembly of the binary to arrive at human-understandable features. Through our results, we identify several interesting features learned by the model and their connection to manually-derived features typically used by traditional machine learning models. Additionally, we explore the impact of training data volume and regularization on the quality of the learned features and the efficacy of the classifiers, revealing the somewhat paradoxical insight that better generalization does not necessarily result in better performance for byte-based malware classifiers.