Abstract
Spam filters typically use optical character recognition (OCR) for extracting the text from images. These days spammers have circumvented optical scanning by fracturing the text within the images thereby improving their attacks and finally reaching to the users. This paper proposes a three-stream deep learning-based model which uses Convolutional Neural Networks (CNN), Transfer Learning, SIFT and HOG features via hybrid fusion framework. Transfer learning alone can only achieve an accuracy of 95% but our hybrid model shows improved performance and obtains an accuracy of 96%, eclipsing the existing techniques. We have created our dataset of challenging HAM images which will be publicly available. On our challenging dataset as well, the proposed method outperforms other existing methods for effectively detecting the spam attacks targeted via images.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Radicati group email statistics report 2021–25. https://www.radicati.com/wp/wp-content/uploads/2021/Email_Statistics_Report,_2021-2025_Executive_Summary.pdf. Accessed 2 Jun 2022
Lai, C.-C., Tsai, M.-C.: An empirical performance comparison of machine learning methods for spam e-mail categorization. In: Fourth International Conference on Hybrid Intelligent Systems (HIS’04), pp. 44–48. IEEE (2004)
Image spam classification using OCR technique. January 2017. Sunita V. Dhavale: https://www.researchgate.net/publication/315388437_Image_Spam_Filters_Based_on_Optical_Character_Recognition_OCR_Techniques
Kumar, A.D., Vinayakumar, R., Soman, K.P.: Deep Learning based Image Spam Detection 3 Oct 2018. https://arxiv.org/abs/1810.03977
Vinayakumar, R., Soman, K., Poornachandran, P., Akarsh, S.: Application of deep learning architectures for cyber security. In: Hassanien, A., Elhoseny, M. (eds) Cybersecurity and Secure Information Systems, pp. 125–160. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-16837-7_7
Venkatraman, S., Alazab, M., Vinayakumar, R.: A hybrid deep learning image-based analysis for effective malware detection. J. Inf. Secur. Appl. 47, 377–389 (2019)
Vinayakumar, R., Alazab, M., Soman, K., Poornachandran, P., Venkatraman, S.: Robust intelligent malware detection using deep learning. IEEE Access 7, 46 717-46 738 (2019)
Mohan, V.S., Vinayakumar, R., Soman, K., Poornachandran, P.: Spoof net: syntactic patterns for identification of ominous online factors. In: 2018 IEEE Security and Privacy Workshops (SPW), pp. 258–263. IEEE (2018)
Vinayakumar, R., Alazab, M., Soman, K., Poornachandran, P., AlNemrat, A., Venkatraman, S.: Deep learning approach for intelligent intrusion detection system. IEEE Access 7, 41 525-41 550 (2019)
ADAM: Kingma, D., Adam, B.J.: A method for stochastic optimization. Comput. Sci. (2014)
Xception: 7 Oct 2016: François Chollet: arXiv:1610.02357v3
Introduction to machine learning with applications in information security. Chapman & Hall/CRC
Dredze, M., Gevaryahu, R., Elias-Bachrach, A.: Learning fast classifiers for image spam. In: CEAS, pp. 2007–487 (2007)
Gao, Y., et al.: Image spam hunter. In: 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1765–1768. IEEE (2008)
ResNet251: He, K., Zhang, X., Ren, S., Sun, J.:10 Dec 2015: arXiv:1512.03385
DenseNet201: https://arxiv.org/abs/1608.06993v5
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kumar, S. et al. (2023). Features Assimilation via Three-Stream Deep Networks for Spam Attack Detection from Images. In: Gupta, D., Bhurchandi, K., Murala, S., Raman, B., Kumar, S. (eds) Computer Vision and Image Processing. CVIP 2022. Communications in Computer and Information Science, vol 1777. Springer, Cham. https://doi.org/10.1007/978-3-031-31417-9_39
Download citation
DOI: https://doi.org/10.1007/978-3-031-31417-9_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-31416-2
Online ISBN: 978-3-031-31417-9
eBook Packages: Computer ScienceComputer Science (R0)