Abstract
As one of the most pervasive current modes of communication, email needs to be fast and reliable. However, spammers and attackers use it as a primary channel to conduct illegal activities. Although many approaches have been developed and evaluated for spam detection, they do not provide sufficient accuracy. This deficiency results in significant economic losses for organizations. In this article, we first propose a framework for creating novel spam filters using Keras to combine a Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) classification models. We then use this framework to introduce a specific solution applicable to realistic scenarios involving dynamic incoming email data in real-time. This solution takes the form of a real-time content-based spam classifier. We evaluate its performance concerning accuracy, precision, recall, false-positive, and false-negative rates. Our experimental results show that our approach can significantly outperform existing solutions for real-time spam detection.
- N. Abroyan. 2017. Convolutional and recurrent neural networks for real-time data classification. In Proceedings of the 7th International Conference on Innovative Computing Technology (INTECH’17). 23–27. DOI:https://doi.org/10.1109/INTECH.2017.8102422Google Scholar
Cross Ref
- N. Abroyan and R. G. Hakobyan. 2016. A review of the usage of machine learning in real-time systems. Proceedings of NPUA Information Technologies Electronics Radio Engineering 19, 1 (2016), 46–54.Google Scholar
- A. Alghoul, S. A. Ajrami, G. A. Jarousha, G. Harb, and S. S. Abu-Naser. 2018. Email classification using artificial neural network. Int. J. Acad. Eng. Res. 2, 11 (2018).Google Scholar
- A. Almomani, S. Atawneh, A. Meulenberg, and E. Almomani. 2013. A survey of phishing email filtering techniques. IEEE Commun. Surv. Tutor. 15 (2013), 2070–2090.Google Scholar
Cross Ref
- A. C. Atluri and V. Tran. 2017. Botnets threat analysis and detection. Inf. Secur. Pract. 123 (2017), 7–28. DOI:https://doi.org/org/10.1007/978-3-319-48947-6_2Google Scholar
- A. Barushka and P. Hajek. 2018. Spam filtering using integrated distribution-based balancing approach and regularized deep neural networks. Appl. Intell. 48, 10 (2018), 3538–3556. Google Scholar
Digital Library
- A. Barushka and P. Hajek. 2019. Review spam detection using word embeddings and deep neural networks. In Proceedings of the IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI’19). 340–350.Google Scholar
- N. Bhargava, G. Sharma, R. Bhargava, and M. Mathuria. 2013. Decision tree analysis on j48 algorithm for data mining. Int. J. Adv. Res.Comput. Sci. Softw. Eng. 3, 6 (2013).Google Scholar
- A. Bhowmick and S. M. Hazarika. E-mail spam filtering: a review of techniques and trends. In Lecture Notes in Electrical Engineering, Vol. 443. pp. 583–590. DOI:https://doi.org/10.1007/978-981-10-4765-7_61Google Scholar
- J. Carson. 2018. Symantec Internet Security Threat Report 2018: The Top Takeaways. Retrieved from https://thycotic.com/company/blog/2018/04/17/symantec-internet-security-threat-report-2018/.Google Scholar
- K. Chen, X. Zou, X. Chen, and H. Wang. 2019. An automated online spam detector based on deep cascade forest). In Proceedings of the International Conference on Science of Cyber Security (SciSec’19). 33–46.Google Scholar
- V. Cihan and M. T. A. Hezha. 2019. Comparison of string matching algorithms on spam email detection. In Proceedings of the International Congress on Big Data, Deep Learning and Fighting Cyber Terrorism (IBIGDELFT’18). DOI:https://doi.org/10.1109/IBIGDELFT.2018.8625317Google Scholar
- E. G. Dada, J. S. Bassi, H. Chiroma, S. M. Abdulhamid, A. O. Adetunmbi, and O. E. Ajibuwa. 2019. Machine learning for email spam filtering: review, approaches and open research problems. Elsevier 5, 6 (2019). DOI:https://doi.org/10.1016/j.heliyon.2019.e01802Google Scholar
- Merriam-Webster Dictionary. 2018. Merriam-Webster Dictionary, “Spam - Definition Spam Use by Merriam-Webster.”Retrieved from https://thycotic.com/company/blog/2018/04/17/symantec-internet-security-threat-report-2018/.Google Scholar
- J. Fernandez-Conde, P. Cuenca-Jimenez, and R. Toldedo-Moreo. 2019. Improving scheduling performance of a real-time system by incorporation of an artificial intelligence planner. In Proceedings of the International Work-Conference on the Interplay Between Natural and Artificial Computation (IWINAC’19). 127–136.Google Scholar
- H. A. Ghada and B. M. Rabiei. 2019. Comparison of four email classification algorithms using WEKA. Int. J. Comput. Sci. Inf. Secur. 17, 2 (2019).Google Scholar
- M. Granik and V. Mesyura. 2017. Fake news detection using naive Bayes classifier. In Proceedings of the IEEE 1st Ukraine Conference on Electrical and Computer Engineering (UKRCON’17). DOI:https://doi.org/10.1109/UKRCON.2017.8100379Google Scholar
- R. Team. 2015. Email Statistics Report. The Radicati Group, Inc. Palo Alto, CA, USA, Mar.2015.Google Scholar
- G. Jain, M. Sharma, and B. Agarwal. 2019. Optimizing semantic LSTM for spam detection. Int. J. Inf. Technol. 11 (2019), 239–250.Google Scholar
Cross Ref
- K. Jiang, S. Feng, Q. Song, R. A. Calix, M. Gupta, and G. R. Bernard. 2018. Identifying tweets of personal health experience through word embedding and LSTM neural network.BMC Bioinf. 19, 210 (2018). DOI:https://doi.org/10.1186/s12859-018-2198-yGoogle Scholar
- S. Kadam, A. Gala, P. Gehlot, A. Kurup, and K. Ghag. 2018. Word embedding based multinomial naive Bayes algorithm for spam filtering. In Proceedings of the 4th International Conference on Computing Communication Control and Automation (ICCUBEA’18). DOI:https://doi.org/10.1109/ICCUBEA.2018.8697601Google Scholar
- Z. Khan and U. Qamar. 2016. Text mining approach to detect spam in emails. In Proceedings of the International Conference on Innovations in Intelligent Systems and Computing Technologies.Google Scholar
- R. Kiran and I. AtmosukartoS. 2005. Spam or Not Spam—That Is the Question. Technical Report. University of Washington.Google Scholar
- A. Kumar and J. P. Singh. 2018. Location reference identification from tweets during emergencies: A deep learning approach. Int. J. Disast. Risk Reduct. 33 (2018), 365–375. DOI:https://doi.org/10.1016/j.ijdrr.2018.10.021Google Scholar
Cross Ref
- D. Kwon, K. Natarajan, S. C. Suh, H. Kim, and J. Kim. 2018. An empirical study on network anomaly detection using convolutional neural networks. In Proceedings of the IEEE 38th International Conference on Distributed Computing Systems (ICDCS’18). DOI:https://doi.org/10.1109/ICDCS.2018.00178Google Scholar
- J. Lu, A. Liu, F. Dong, F. Gu, J. Gama, and G. Zhang. 2019. Learning under concept drift: A review. IEEE Trans. Knowl. Data Eng. 31, 12 (2019), 2346–2363. DOI:https://doi.org/10.1109/TKDE.2018.2876857Google Scholar
- M. Popovac, M. Karanovic, S. Sladojevic, M. Arsenovic, and A. Anderla. 2018. Convolutional neural network based SMS spam detection. In Proceedings of the 26th Telecommunications Forum (TELFOR’18). DOI:https://doi.org/10.1109/TELFOR.2018.8611916Google Scholar
Cross Ref
- J. Ramos. 2003. Using TF-IDF to determine word relevance in document queries. In Proceedings of the 1st Instructional Conference on Machine Learning. 133–142.Google Scholar
- R. M. Ravindran and A. S. Thanamani. 2015. K-means document clustering using vector space model. Bonfring Int. J. Data Mining 5, 2 (2015), 10–14.Google Scholar
Cross Ref
- R. Ruskanda and F. Zakhralativa. 2019. Study on the effect of pre-processing methods for spam email detection. Indon. J. Comput.1 (2019), 109–118.Google Scholar
- N. Saidani, K. Adi, and M. S. Allili. 2017. A supervised approach for spam detection using text-based semantic representation. In Proceedings of the International Conference on E-Technologies (MCETECH’17), Vol. 289. Springer, Cham, 136–148.Google Scholar
Cross Ref
- G. Schryen. 2007. 2007 anti-spam measures. In 2Anti-Spam Measures. Springer, Berlin, 178. DOI:https://doi.org/10.1007/978-3-540-71750-8_4%7DGoogle Scholar
- P. Sethi, V. Bhandari, and B. Kohli. 2017. SMS spam detection and comparison of various machine learning algorithms. In Proceedings of the International Conference on Computing and Communication Technologies for Smart Nation (IC3TSN’17).Google Scholar
- M. Shuaib, O. Osho, I. Ismaila, and J. K. Alhassan. 2018. Comparative analysis of classification algorithms for email spam detection. Int. J. Comput. Netw. Inf. Secur. 10, 1 (2018), 60–67.Google Scholar
- R. Varghese and K. A. Dhanya. 2017. Efficient feature set for spam Email filtering. In Proceedings of the IEEE 7th International Advance Computing Conference (IACC’17). 732–737.Google Scholar
Cross Ref
- L. Vrizlynn. 2017. IEEE 802.11 network anomaly detection and attack classification: a deep learning approach. In Proceedings of the IEEE Wireless Communications and Networking Conference (WCNC’17). DOI:https://doi.org/10.1109/WCNC.2017.7925567Google Scholar
- Y. Wang, F. Yu, and Y. Wei. 2018. Research of email classification based on deep neural network. In Proceedings of the 2nd International Conference of Sensor Network and Computer Engineering (ICSNCE’18). DOI:https://doi.org/10.2991/icsnce-18.2018.16Google Scholar
- H. Yang, Q. Liu, S. Zhou, and Y. Luo. 2019. A spam filtering method based on multi-modal fusion. Appl. Sci. 9, 6 (2019). DOI:https://doi.org/10.3390/app9061152Google Scholar
- B. Zhang, G. Zhao, Y. Feng, X. Zhang, W. Jiang, J. Dai, and J. Gao. 2016. Behavior analysis based SMS spammer detection in mobile communication networks. In Proceedings of the IEEE 1st International Conference on Data Science in Cyberspace (DSC’16). 2–7.Google Scholar
- I. Zliobaite, M. Pechenizkiy, and J. Gama. 2016. An overview of concept drift applications. Big Data Anal.: New Algor. New Soc. 16 (2016), 91–114.Google Scholar
Cross Ref
Index Terms
A Novel Real-time Anti-spam Framework
Recommendations
Analyzing fusion of regularization techniques in the deep learning‐based intrusion detection system
AbstractThe surge of constantly evolving network attacks can be addressed by designing an effective and efficient Intrusion Detection System (IDS). Various Deep Learning (DL) techniques have been used for designing intelligent IDS. However, DL techniques ...
The sound of intrusion: A novel network intrusion detection system
AbstractA network intrusion detection system is an essential part of network security research. It detects intrusion behaviors through active defense technology and takes emergency measures such as alerting and terminating intrusions. To this ...
Graphical abstractDisplay Omitted
Highlights- Deep-learning-based NIDS has been proven to be successful and effective.
- ...
Efficient Deep CNN-BiLSTM Model for Network Intrusion Detection
AIPR '20: Proceedings of the 2020 3rd International Conference on Artificial Intelligence and Pattern RecognitionThe need for Network Intrusion Detection systems has risen since usage of cloud technologies has become mainstream. With the ever growing network traffic, Network Intrusion Detection is a critical part of network security and a very efficient NIDS is a ...






Comments