# Imbalanced Malware Images Classification: a CNN based Approach

arXiv: https://arxiv.org/abs/1708.08042 · HTML: https://mlsanity.com/paper/1708.08042/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2017.

## Built on by (most cited first, 15 of 15)

- [CNS-Net: Conservative Novelty Synthesizing Network for Malware Recognition in an Open-set Scenario](https://mlsanity.com/paper/2305.01236/) (2023)
- [MalNet: A Large-Scale Image Database of Malicious Software](https://mlsanity.com/paper/2102.01072/) (2021)
- [MDENet: Multi-modal Dual-embedding Networks for Malware Open-set Recognition](https://mlsanity.com/paper/2305.01245/) (2023)
- [Rediscovering BCE Loss for Uniform Classification](https://mlsanity.com/paper/2403.07289/) (2024)
- [Malware Detection Using Frequency Domain-Based Image Visualization and Deep Learning](https://mlsanity.com/paper/2101.10578/) (2021)
- [Margin-bounded Confidence Scores for Out-of-Distribution Detection](https://mlsanity.com/paper/2410.07185/) (2024)
- [Auxiliary-Classifier GAN for Malware Analysis](https://mlsanity.com/paper/2107.01620/) (2021)
- [Deep Multi-Task Learning for Malware Image Classification](https://mlsanity.com/paper/2405.05906/) (2024)
- [Towards Interpretable Ensemble Learning for Image-based Malware Detection](https://mlsanity.com/paper/2101.04889/) (2021)
- [Classification of Alzheimer's Disease Using the Convolutional Neural Network (CNN) with Transfer Learning and Weighted Loss](https://mlsanity.com/paper/2207.01584/) (2022)
- [On deceiving malware classification with section injection](https://mlsanity.com/paper/2208.06092/) (2022)
- [Sequential Embedding-based Attentive (SEA) classifier for malware classification](https://mlsanity.com/paper/2302.05728/) (2023)
- [Generative AI-Based Effective Malware Detection for Embedded Computing Systems](https://mlsanity.com/paper/2404.02344/) (2024)
- [A Visualized Malware Detection Framework with CNN and Conditional GAN](https://mlsanity.com/paper/2409.14439/) (2024)
- [ThreatVisionAI: A Hybrid CNN-ViT Framework for Image-Based Malware Classification](https://mlsanity.com/paper/2607.03653/) (2026)

## Abstract (arXiv)

Deep convolutional neural networks (CNNs) can be applied to malware binary detection via image classification. The performance, however, is degraded due to the imbalance of malware families (classes). To mitigate this issue, we propose a simple yet effective weighted softmax loss which can be employed as the final layer of deep CNNs. The original softmax loss is weighted, and the weight value can be determined according to class size. A scaling parameter is also included in computing the weight. Proper selection of this parameter is studied and an empirical option is suggested. The weighted loss aims at alleviating the impact of data imbalance in an end-to-end learning fashion. To validate the efficacy, we deploy the proposed weighted loss in a pre-trained deep CNN model and fine-tune it to achieve promising results on malware images classification. Extensive experiments also demonstrate that the new loss function can well fit other typical CNNs, yielding an improved classification performance.