MalNet: A Large-Scale Image Database of Malicious Software
Not on the map. Why?
Abstract (arXiv)
Computer vision is playing an increasingly important role in automated malware detection with the rise of the image-based binary representation. These binary images are fast to generate, require no feature engineering, and are resilient to popular obfuscation methods. Significant research has been conducted in this area, however, it has been restricted to small-scale or private datasets that only a few industry labs and research teams have access to. This lack of availability hinders examination of existing work, development of new research, and dissemination of ideas. We release MalNet-Image, the largest public cybersecurity image database, offering 24x more images and 70x more classes than existing databases (available at https://mal-net.org). MalNet-Image contains over 1.2 million malware images -- across 47 types and 696 families -- democratizing image-based malware capabilities by enabling researchers and practitioners to evaluate techniques that were previously reported in propriety settings. We report the first million-scale malware detection results on binary images. MalNet-Image unlocks new and unique opportunities to advance the frontiers of machine learning, enabling new research directions into vision-based cyber defenses, multi-class imbalanced classification, and interpretable security.
Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 17 of its 58 references that are in the map. First posted on arXiv 31 Jan 2021.
Builds on
17 of 58 references.
References · 17
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2016Densely Connected Convolutional Networkscited by 6,691
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
- 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
- 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
- 2017Malware Detection by Eating a Whole EXEcited by 114
- 2020A Large-Scale Database for Graph Representation Learningcited by 54
- 2018Microsoft Malware Classification Challengecited by 46
- 2020ELF: An Early-Exiting Framework for Long-Tailed Classificationcited by 20
- 2017Imbalanced Malware Images Classification: a CNN based Approachcited by 15
- 2018Lightweight Classification of IoT Malware based on Image Recognitioncited by 13
- 2020Data Augmentation Based Malware Detection using Convolutional Neural Networkscited by 8
5 more
- 2018Deep Transfer Learning for Static Malware Classificationcited by 7
- 2020REST: Robust and Efficient Neural Networks for Sleep Monitoring in the Wildcited by 7
- 2017AndroZoo++: Collecting Millions of Android Apps and Their Metadata for the Research Communitycited by 3
- 2020D2M: Dynamic Defense and Modeling of Adversarial Movement in Networkscited by 2
- 2019New Era of Deeplearning-Based Malware Intrusion Detection: The Malware Detection and Prediction Based On Deep Learningcited by 1
Built on by
Citing papers per year: 2023: 1; 2024: 3; 2025: 3; 2026: 4.
11 papers.
- 2024Position: Graph Foundation Models are Already Herecited by 84
- 2024AI-Driven Guided Response for Security Operation Centers with Microsoft Copilot for Securitycited by 7
- 2023A Poincar'e Inequality and Consistency Results for Signal Sampling on Large Graphscited by 1
- 2026Automated Malware Family Classification using Weighted Hierarchical Ensembles of Large Language Modelscited by 1
- 2024Web Scale Graph Mining for Cyber Threat Intelligencecited by 0
- 2025MalVol-25: A Diverse, Labelled and Detailed Volatile Memory Dataset for Malware Detection and Response Testing and Validationcited by 0
- 2025Evaluating Out-of-Distribution Robustness in Graph-Based Android Malware Classification: A New Principled Benchmarkcited by 0
- 2025Federated Cyber Defense: Privacy-Preserving Ransomware Detection Across Distributed Systemscited by 0
- 2026GoCoMA: Hyperbolic Multimodal Representation Fusion for Large Language Model-Generated Code Attributioncited by 0
- 2026TUANDROMD-X: Advanced Entropy and Visual Analytics Dataset for Enhanced Malware Detection and Classificationcited by 0
- 2026MalTree: Tracing Malware Evolution from Embeddings at Scalecited by 0
- 2026MalTree: Tracing Malware Evolution from Embeddings at Scale4 Jun 2026
- 2026TUANDROMD-X: Advanced Entropy and Visual Analytics Dataset for Enhanced Malware Detection and Classification7 May 2026
- 2026Automated Malware Family Classification using Weighted Hierarchical Ensembles of Large Language Models2 Apr 2026
- 2026GoCoMA: Hyperbolic Multimodal Representation Fusion for Large Language Model-Generated Code Attribution24 Mar 2026
- 2025Federated Cyber Defense: Privacy-Preserving Ransomware Detection Across Distributed Systems3 Nov 2025
- 2025Evaluating Out-of-Distribution Robustness in Graph-Based Android Malware Classification: A New Principled Benchmark8 Aug 2025
- 2025MalVol-25: A Diverse, Labelled and Detailed Volatile Memory Dataset for Malware Detection and Response Testing and Validation5 Jul 2025
- 2024Web Scale Graph Mining for Cyber Threat Intelligence9 Nov 2024
- 2024AI-Driven Guided Response for Security Operation Centers with Microsoft Copilot for Security12 Jul 2024
- 2024Position: Graph Foundation Models are Already Here3 Feb 2024
- 2023A Poincar'e Inequality and Consistency Results for Signal Sampling on Large Graphs17 Nov 2023