Skip to main content
Springer Nature Link
Log in

Lightweight CNN-based malware image classification for resource-constrained applications

  • S.I. : Low Resource Machine Learning Algorithms (LR-MLA)
  • Published:
Innovations in Systems and Software Engineering Aims and scope Submit manuscript

Abstract

Malware (Malicious Software) is a malicious piece of code designed with the intention to enter a computer system to carry out harmful operations. It poses a severe threat to computer and internet users. As the number of new malwares increases, the challenge of identifying and classifying them into appropriate families gets more difficult. During the last couple of years, deep convolutional neural network (CNN)-based models resulted promising performance on malware classification. However, the existing deep CNN-based approaches require higher resources in terms of storage and computationally heavy training operations for feeding a large number of data to the CNN model. As a result, the existing approaches are not suitable for malware detection in Internet of things (IoT) applications as IoT-based applications are mostly resource-constrained in nature. To address this issue, exploring lightweight deep learning models for malware detection in resource-constrained devices without compromising accuracy is required. In this regard, the current work proposes a custom lightweight deep convolutional neural network for malware image classification. The proposed technique is used to extract the characteristic features of the malware sample and use the extracted features to classify them into their corresponding malware families by feeding an image to proposed CNN model with Adam optimizer as an input. This furnishes useful information for human analysts without prior knowledge and can be deployed efficiently in IoT applications to aid in developing protection against malwares. The model is validated through multiple trials, demonstrating that the model achieves 96.64% accuracy. The designed CNN model is extremely lightweight and hence can be aptly fit in resource-constrained applications.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Ye Y, Li T, Adjeroh D, Iyengar SS (2017) A survey on malware detection using data mining techniques. ACM Comput Surv (CSUR) 50(3):1–40

    Article  MATH  Google Scholar 

  2. Jain M, Andreopoulos W, Stamp M (2021) Cnn vs elm for image-based malware classification. arXiv preprint arXiv:2103.13820

  3. Choi S-Y, Lim CG, Kim Y-M (2019) Automated link tracing for classification of malicious websites in malware distribution networks. J Inf Process Syst 15(1):100–115

    MATH  Google Scholar 

  4. Ahmadi M, Ulyanov D, Semenov S, Trofimov M, Giacinto G (2016) Novel feature extraction, selection and fusion for effective malware family classification. In: Proceedings of the sixth ACM conference on data and application security and privacy, pp 183–194

  5. Kalash M, Rochan M, Mohammed N, Bruce ND, Wang Y, Iqbal F (2018) Malware classification with deep convolutional neural networks. In: 2018 9th IFIP international conference on new technologies, mobility and security (NTMS). IEEE, pp 1–5

  6. Le Q, Boydell O, Mac Namee B, Scanlon M (2018) Deep learning at the shallow end: malware classification for non-domain experts. Digit Investig 26:118–126

    Article  Google Scholar 

  7. Cui Z, Xue F, Cai X, Cao Y, Wang G-G, Chen J (2018) Detection of malicious code variants based on deep learning. IEEE Trans Industr Inf 14(7):3187–3196

    Article  MATH  Google Scholar 

  8. Yakura H, Shinozaki S, Nishimura R, Oyama Y, Sakuma J (2019) Neural malware analysis with attention mechanism. Comput Secur 87:101592

    Article  Google Scholar 

  9. Rezende E, Ruppert G, Carvalho T, Ramos F, De Geus P (2017) Malicious software classification using transfer learning of resnet-50 deep neural network. In: 2017 16th IEEE international conference on machine learning and applications (ICMLA). IEEE, pp 1011–1014

  10. Gao X, Hu C, Shan C, Liu B, Niu Z, Xie H (2020) Malware classification for the cloud via semi-supervised transfer learning. J Inf Secur Appl 55:102661

    MATH  Google Scholar 

  11. Darem A, Abawajy J, Makkar A, Alhashmi A, Alanazi S (2021) Visualization and deep-learning-based malware variant detection using opcode-level features. Futur Gener Comput Syst 125:314–323

    Article  Google Scholar 

  12. Marastoni N, Giacobazzi R, Dalla Preda M (2021) Data augmentation and transfer learning to classify malware images in a deep learning context. J Comput Virol Hacking Tech 17:1–19

    MATH  Google Scholar 

  13. Yan J, Qi Y, Rao Q (2018) Detecting malware with an ensemble method based on deep neural network. Secur Commun Netw 2018

  14. Khan RU, Zhang X, Kumar R (2019) Analysis of resnet and googlenet models for malware detection. J Comput Virol Hacking Tech 15(1):29–37

    Article  MATH  Google Scholar 

  15. Vinayakumar R, Alazab M, Soman K, Poornachandran P, Al-Nemrat A, Venkatraman S (2019) Deep learning approach for intelligent intrusion detection system. IEEE Access 7:41525–41550

    Article  Google Scholar 

  16. Namanya AP, Awan IU, Disso JP, Younas M (2020) Similarity hash based scoring of portable executable files for efficient malware detection in IoT. Futur Gener Comput Syst 110:824–832

    Article  Google Scholar 

  17. Darwish A, Ezzat D, Hassanien AE (2020) An optimized model based on convolutional neural networks and orthogonal learning particle swarm optimization algorithm for plant diseases diagnosis. Swarm Evol Comput 52:100616

    Article  MATH  Google Scholar 

  18. Venkatraman S, Alazab M, Vinayakumar R (2019) A hybrid deep learning image-based analysis for effective malware detection. J Inf Secur Appl 47:377–389

    Google Scholar 

  19. Çayır A, Ünal U, Dağ H (2021) Random capsnet forest model for imbalanced malware type classification task. Comput Secur 102:102133

    Article  MATH  Google Scholar 

  20. Naeem H, Ullah F, Naeem MR, Khalid S, Vasan D, Jabbar S, Saeed S (2020) Malware detection in industrial internet of things based on hybrid image visualization and deep learning model. Ad Hoc Netw 105:102154

    Article  MATH  Google Scholar 

  21. Go JH, Jan T, Mohanty M, Patel OP, Puthal D, Prasad M (2020) Visualization approach for malware classification with resnext. In: 2020 IEEE congress on evolutionary computation (CEC). IEEE, pp 1–7

  22. Kumar S et al (2021) Mcft-cnn: malware classification with fine-tune convolution neural networks using traditional and transfer learning in internet of things. Futur Gener Comput Syst 125:334–351

    Article  MATH  Google Scholar 

Download references

Author information

Author notes

  1. Ashlesha Hota, Subir Panja and Amitava Nag contributed equally to this work.

Authors and Affiliations

  1. Computer Science and Engineering, Central Institute of Technology, Kokrajhar, Assam, 783370, India

    Ashlesha Hota, Subir Panja & Amitava Nag

Authors
  1. Ashlesha Hota
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Subir Panja
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Amitava Nag
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding authors

Correspondence to Subir Panja or Amitava Nag.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hota, A., Panja, S. & Nag, A. Lightweight CNN-based malware image classification for resource-constrained applications. Innovations Syst Softw Eng 21, 1–14 (2025). https://doi.org/10.1007/s11334-022-00461-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11334-022-00461-7

Keywords