Downloads · 30 days
0
ResNet1DV2_152D_SE_MalNet_Signal_Binary
jackwilkie/ResNet1DV2_152D_SE_MalNet_Signal_Binary
ResNet1DV2_152D_SE_MalNet_Signal_Binary is a machine learning model from jackwilkie. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Pretrained ResNet1DV2-152D-SE model for classing malware signals as described by this paper.
Access
Public
Updated Sep 21, 2025
Repo size
1.3 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.tar1.3 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Sep 20, 2025
- Updated
- Sep 21, 2025
- SHA
- 4202389d
Datasets
Model card
From the Hugging Face model README
ResNet1DV2-152D-SE for binary-level classification on MalNet Signal
Pretrained ResNet1DV2-152D-SE model for classing malware signals as described by this paper.
The full code bases, including training and evaluation proceedure, is available here.
Malware Signals
Malware signals are 1D representations of the bytecode of an executable which act as an alternative to byteplot images as input to machine learning models. These signals can be statically extracted from various formated (e.g. EXE, APK), and used to train a 1D CNN for malware classification. By using a 1D representation of the binaries, more information from the original binary is preserved and the addition of spurious spatial correlation is avoided, resulting in improved downstream model performance. A comparison of malware signals with byteplot images is shown below:
<p align="center"> <img src="https://cdn-uploads.huggingface.co/production/uploads/68c7f421fc90bcc7a409d4f1/zoS8dD_FGBNenuTpErIkt.png" width="700" /> </p>Model Details
<p align="center"> <img src="https://cdn-uploads.huggingface.co/production/uploads/68c7f421fc90bcc7a409d4f1/if3ZhzEhIfoEpg1128B5t.png" width="700" /> </p>The model is a ResNet152 model with a deep stem and squeeze-and-excitation layers which has been adapted to operate on 1D signals by replacing the 2D convolutions with 1D convolutions, and squaring the kernel sizes and stride values.
Results
ResNet1DV2-152D-SE outperforms all existing 2D models on MalNet binary, type, and family level classification:
<table style="border-collapse:collapse; font-family:system-ui, -apple-system, Segoe UI, Roboto, Arial, sans-serif; font-size:14px;"> <thead> <tr> <th rowspan="2" style="text-align:left; padding:8px 10px;">Model</th> <th colspan="3" style="padding:8px 10px; border-left:1px solid #ddd; text-align:center; border-bottom:0;">Binary</th> <th colspan="3" style="padding:8px 10px; border-left:1px solid #ddd; text-align:center; border-bottom:0;">Type</th> <th colspan="3" style="padding:8px 10px; border-left:1px solid #ddd; text-align:center; border-bottom:0;">Family</th> </tr> <tr> <th style="padding:6px 10px; border-left:1px solid #ddd; text-align:center;">F1 Score</th> <th style="padding:6px 10px; text-align:center;">Precision</th> <th style="padding:6px 10px; text-align:center;">Recall</th> <th style="padding:6px 10px; border-left:1px solid #ddd; text-align:center;">F1 Score</th> <th style="padding:6px 10px; text-align:center;">Precision</th> <th style="padding:6px 10px; text-align:center;">Recall</th> <th style="padding:6px 10px; border-left:1px solid #ddd; text-align:center;">F1 Score</th> <th style="padding:6px 10px; text-align:center;">Precision</th> <th style="padding:6px 10px; text-align:center;">Recall</th> </tr> </thead> <tbody> <tr> <td style="padding:6px 10px;"><strong>ResNet1DV2-152D-SE</strong></td> <!-- Binary --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;"><strong>.874</strong></td> <td style="padding:6px 10px; text-align:center;">.907</td> <td style="padding:6px 10px; text-align:center;"><strong>.846</strong></td> <!-- Type --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;"><strong>.503</strong></td> <td style="padding:6px 10px; text-align:center;"><strong>.643</strong></td> <td style="padding:6px 10px; text-align:center;"><strong>.453</strong></td> <!-- Family --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;"><strong>.507</strong></td> <td style="padding:6px 10px; text-align:center;"><strong>.580</strong></td> <td style="padding:6px 10px; text-align:center;"><strong>.480</strong></td> </tr> <tr> <td style="padding:6px 10px;">SHERLOCK</td> <!-- Binary --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.854</td> <td style="padding:6px 10px; text-align:center;"><strong>.920</strong></td> <td style="padding:6px 10px; text-align:center;">.810</td> <!-- Type --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.497</td> <td style="padding:6px 10px; text-align:center;">.628</td> <td style="padding:6px 10px; text-align:center;">.447</td> <!-- Family --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.491</td> <td style="padding:6px 10px; text-align:center;">.568</td> <td style="padding:6px 10px; text-align:center;">.461</td> </tr> <!-- Added rows --> <tr> <td style="padding:6px 10px;">ResNet18</td> <!-- Binary --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.862</td> <td style="padding:6px 10px; text-align:center;">.893</td> <td style="padding:6px 10px; text-align:center;">.837</td> <!-- Type --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.467</td> <td style="padding:6px 10px; text-align:center;">.556</td> <td style="padding:6px 10px; text-align:center;">.424</td> <!-- Family --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.454</td> <td style="padding:6px 10px; text-align:center;">.538</td> <td style="padding:6px 10px; text-align:center;">.423</td> </tr> <tr> <td style="padding:6px 10px;">ResNet50</td> <!-- Binary --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.854</td> <td style="padding:6px 10px; text-align:center;">.907</td> <td style="padding:6px 10px; text-align:center;">.814</td> <!-- Type --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.479</td> <td style="padding:6px 10px; text-align:center;">.566</td> <td style="padding:6px 10px; text-align:center;">.441</td> <!-- Family --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.468</td> <td style="padding:6px 10px; text-align:center;">.541</td> <td style="padding:6px 10px; text-align:center;">.443</td> </tr> <tr> <td style="padding:6px 10px;">DenseNet121</td> <!-- Binary --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.864</td> <td style="padding:6px 10px; text-align:center;">.900</td> <td style="padding:6px 10px; text-align:center;">.834</td> <!-- Type --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.471</td> <td style="padding:6px 10px; text-align:center;">.558</td> <td style="padding:6px 10px; text-align:center;">.428</td> <!-- Family --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.461</td> <td style="padding:6px 10px; text-align:center;">.529</td> <td style="padding:6px 10px; text-align:center;">.438</td> </tr> <tr> <td style="padding:6px 10px;">Densenet169</td> <!-- Binary --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.864</td> <td style="padding:6px 10px; text-align:center;">.890</td> <td style="padding:6px 10px; text-align:center;">.841</td> <!-- Type --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.477</td> <td style="padding:6px 10px; text-align:center;">.573</td> <td style="padding:6px 10px; text-align:center;">.433</td> <!-- Family --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.462</td> <td style="padding:6px 10px; text-align:center;">.545</td> <td style="padding:6px 10px; text-align:center;">.434</td> </tr> <tr> <td style="padding:6px 10px;">MobileNetV2(x.5)</td> <!-- Binary --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.857</td> <td style="padding:6px 10px; text-align:center;">.894</td> <td style="padding:6px 10px; text-align:center;">.827</td> <!-- Type --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.460</td> <td style="padding:6px 10px; text-align:center;">.547</td> <td style="padding:6px 10px; text-align:center;">.424</td> <!-- Family --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.451</td> <td style="padding:6px 10px; text-align:center;">.528</td> <td style="padding:6px 10px; text-align:center;">.423</td> </tr> <tr> <td style="padding:6px 10px;">MobileNetV2(x1)</td> <!-- Binary --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.854</td> <td style="padding:6px 10px; text-align:center;">.889</td> <td style="padding:6px 10px; text-align:center;">.825</td> <!-- Type --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.452</td> <td style="padding:6px 10px; text-align:center;">.527</td> <td style="padding:6px 10px; text-align:center;">.419</td> <!-- Family --> <td style="padding:6px 10px; text-align:center; border-left:1px solid #ddd;">.438</td> <td style="padding:6px 10px; text-align:center;">.532</td> <td style="padding:6px 10px; text-align:center;">.405</td> </tr> </tbody> </table>Citation
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->BibTeX:
@misc{wilkie2025signalbasedmalwareclassificationusing,
title={Signal-Based Malware Classification Using 1D CNNs},
author={Jack Wilkie and Hanan Hindy and Ivan Andonovic and Christos Tachtatzis and Robert Atkinson},
year={2025},
eprint={2509.06548},
archivePrefix={arXiv},
primaryClass={cs.CR},
url={https://arxiv.org/abs/2509.06548},
}
APA:
Wilkie, J., Hindy, H., Andonovic, I., Tachtatzis, C., & Atkinson, R. (2025). Signal-Based Malware Classification Using 1D CNNs. arXiv [Cs.CR]. Retrieved from http://arxiv.org/abs/2509.06548
- License
- apache-2.0
- Created
- Sep 20, 2025
- Updated
- Sep 21, 2025