{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T15:58:45Z","timestamp":1777046325347,"version":"3.51.4"},"reference-count":33,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T00:00:00Z","timestamp":1776988800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>The growing complexity of unwanted messages, especially SMS spam, presents a serious challenge to the security of digital communication and user experience. While conventional spam detection models are useful on clean datasets, they are vulnerable to targeted attacks that aim to evade detection. This study is motivated by the urgent need to evaluate the resilience of machine learning models against evolving threats in real-world applications. We specifically investigate the robustness and interpretability of a Multinomial Naive Bayes (MNB) model, representative of traditional machine learning, and a Tiny Text convolutional neural network (Tiny Text CNN), representative of deep learning models, for SMS spam detection. Using the UCI dataset under simulated adversarial text attacks, both models were tested against filler-word insertion and character-level perturbation attacks. Results show that while the Tiny Text CNN maintained higher overall robustness (accuracy: 0.9821 clean vs. 0.9758 under character attacks), both models experienced notable degradation in recall, with MNB being more susceptible to filler-word attacks. Interpretability analyses using LIME and gradient-based saliency maps indicated that adversarial perturbations alter feature importance, diminishing the influence of spam-indicative tokens. The findings underscore the trade-offs between model complexity and adversarial resilience, offering insights for developing more secure and interpretable spam detection systems.<\/jats:p>","DOI":"10.3390\/info17050408","type":"journal-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T14:28:23Z","timestamp":1777040903000},"page":"408","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Analysis of Robustness and Interpretability of Multinomial Na\u00efve Bayes and Tiny Text CNN Models for SMS Spam Detection Under Adversarial Attacks"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3558-6737","authenticated-orcid":false,"given":"Murad A.","family":"Rassam","sequence":"first","affiliation":[{"name":"Department of Information Technology, College of Computer, Qassim University, Buraydah 52571, Saudi Arabia"},{"name":"Faculty of Engineering and Information Technology, Taiz University, Taiz 6803, Yemen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Redhwan","family":"Shaddad","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Information Technology, Taiz University, Taiz 6803, Yemen"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1080\/17517575.2021.1896786","article-title":"A survey of phishing attack techniques, defence mechanisms and open research challenges","volume":"16","author":"Jain","year":"2022","journal-title":"Enterp. Inf. Syst."},{"key":"ref_2","first-page":"1","article-title":"Towards SMS Spam Filtering: Results Under a New Dataset","volume":"2","author":"Almeida","year":"2018","journal-title":"Int. J. Inf. Secur. Science"},{"key":"ref_3","first-page":"1","article-title":"Adversarial Attacks on Deep-learning Models in Natural Language Processing","volume":"11","author":"Zhang","year":"2020","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Biggio, B., and Roli, F. (2018). Wild patterns: Ten years after the rise of adversarial machine learning half-day tutorial. ACM Conference on Computer and Communications Security, Association for Computing Machinery.","DOI":"10.1145\/3243734.3264418"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI","volume":"58","author":"Arrieta","year":"2020","journal-title":"Inf. Fusion"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Slack, D., Hilgard, S., Jia, E., Singh, S., and Lakkaraju, H. (2020). Fooling LIME and SHAP: Adversarial attacks on post hoc explanation methods. AIES 2020\u2014Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society, Association for Computing Machinery.","DOI":"10.1145\/3375627.3375830"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Escalante, H. (2018). Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges. Explainable and Interpretable Models in Computer Vision and Machine Learning, Springer. The Springer Series on Challenges in Machine Learning.","DOI":"10.1007\/978-3-319-98131-4"},{"key":"ref_8","unstructured":"Alvarez-Melis, D., and Jaakkola, T.S. (2018). On the Robustness of Interpretability Methods. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Arora, Y., Gupta, N., Rathore, Y.S., Bansal, N., Mehta, A., Chadha, S., and Kumar, A. (2025). SMS Spam Detection using Advance Naive-Bayes Approach. Proceedings of the 2025 International Conference on Pervasive Computational Technologies, ICPCT 2025, Institute of Electrical and Electronics Engineers Inc.","DOI":"10.1109\/ICPCT64145.2025.10940832"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Nagare, S.M., Dapke, P.P., Quadri, S.A., Bandal, S.B., and Baheti, M.R. (2024). Short Message Service (SMS) Mobile Spam Detection using Na\u00efve Bayes. Proceedings of the 2024 5th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2024, Institute of Electrical and Electronics Engineers Inc.","DOI":"10.1109\/ICMCSI61536.2024.00016"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1016\/j.future.2019.09.001","article-title":"Deep learning to filter SMS Spam","volume":"102","author":"Roy","year":"2020","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_12","unstructured":"Gomaa, W.H. (2026, February 23). The Impact of Deep Learning Techniques on SMS Spam Filtering. Available online: www.ijacsa.thesai.org."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"80253","DOI":"10.1109\/ACCESS.2021.3081479","article-title":"A Spam Transformer Model for SMS Spam Detection","volume":"9","author":"Liu","year":"2021","journal-title":"IEEE Access"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Su, L., Liu, Y., Chen, F., Zhang, Y., Zhao, H., and Zeng, Y. (2022). Adversarial Sample Generation Method for Spam SMS Classification. Proceedings of the 2022 IEEE\/WIC\/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2022, Institute of Electrical and Electronics Engineers Inc.","DOI":"10.1109\/WI-IAT55865.2022.00149"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"24306","DOI":"10.1109\/ACCESS.2024.3364671","article-title":"Investigating Evasive Techniques in SMS Spam Filtering: A Comparative Analysis of Machine Learning Models","volume":"12","author":"Salman","year":"2024","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"176901","DOI":"10.1109\/ACCESS.2025.3620751","article-title":"Textual, Non-Textual, and Hybrid Feature Engineering for SMS Spam Classification","volume":"13","author":"Verma","year":"2025","journal-title":"IEEE Access"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1504","DOI":"10.1016\/j.dcan.2025.07.008","article-title":"ExplainableDetector: Exploring transformer-based language modeling approach for SMS spam detection with explainability analysis","volume":"11","author":"Uddin","year":"2025","journal-title":"Digit. Commun. Netw."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1016\/j.procs.2024.05.046","article-title":"Towards Transparent Cybersecurity: The Role of Explainable AI in Mitigating Spam Threats","volume":"236","author":"Filali","year":"2024","journal-title":"Procedia Comput. Sci."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"100466","DOI":"10.1016\/j.fraope.2025.100466","article-title":"Explainable AI for SMS spam filtering: A novel hybrid architecture combining fuzzy logic and bidirectional LSTM networks","volume":"14","author":"Jasim","year":"2026","journal-title":"Frankl. Open"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"15596","DOI":"10.48084\/etasr.7901","article-title":"Explainable AI-based Framework for Efficient Detection of Spam from Text using an Enhanced Ensemble Technique","volume":"14","author":"Alzahrani","year":"2024","journal-title":"Eng. Technol. Appl. Sci. Res."},{"key":"ref_21","first-page":"79","article-title":"SMS spam detection using BERT and multi-graph convolutional networks","volume":"6","author":"Shen","year":"2025","journal-title":"Int. J. Intell. Netw."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ghourabi, A., and Alohaly, M. (2023). Enhancing Spam Message Classification and Detection Using Transformer-Based Embedding and Ensemble Learning. Sensors, 23.","DOI":"10.3390\/s23083861"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3538491","article-title":"SpotSpam: Intention Analysis-driven SMS Spam Detection Using BERT Embeddings","volume":"16","author":"Oswald","year":"2022","journal-title":"ACM Trans. Web"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"144","DOI":"10.9734\/jamcs\/2023\/v38i101832","article-title":"SMS Spam Detection and Classification to Combat Abuse in Telephone Networks Using Natural Language Processing","volume":"38","author":"Oyeyemi","year":"2023","journal-title":"J. Adv. Math. Comput. Sci."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Ghourabi, A., Mahmood, M.A., and Alzubi, Q.M. (2020). A hybrid CNN-LSTM model for SMS spam detection in arabic and english messages. Future Internet, 12.","DOI":"10.3390\/fi12090156"},{"key":"ref_26","unstructured":"Hoto\u011flu, E., Sen, S., and Can, B. (2025). A Comprehensive Analysis of Adversarial Attacks against Spam Filters. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"112749","DOI":"10.1109\/ACCESS.2025.3581131","article-title":"SMART: Semantic, Multi-Objective, and Reinforcement-Based Adversarial Training for Email Spam Detection","volume":"13","author":"Taha","year":"2025","journal-title":"IEEE Access"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Gao, J., Lanchantin, J., Soffa, M.L., and Qi, Y. (2018, January 24). Black-Box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers. Proceedings of the 2018 IEEE Security and Privacy Workshops (SPW), San Francisco, CA, USA.","DOI":"10.1109\/SPW.2018.00016"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Almeida, T.A., Hidalgo, J.M.G., and Yamakami, A. (2011, January 19\u201322). Contributions to the study of SMS spam filtering: New collection and results. Proceedings of the 2011 ACM Symposium on Document Engineering, Mountain View, CA, USA.","DOI":"10.1145\/2034691.2034742"},{"key":"ref_30","unstructured":"Sahami, M., Dumais, S., Heckerman, D., Horvitz, E., and Building, G. (2026, February 07). A Bayesian Approach to Filtering Junk E-Mail. Available online: https:\/\/audentia-gestion.fr\/MICROSOFT\/PDF\/spam.pdf."},{"key":"ref_31","unstructured":"Mccallum, A., and Nigam, K. (1998). A Comparison of Event Models for Naive Bayes Text Classiication, The Association for the Advancement of Artificial Intelligence."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Kim, Y. (2014). Convolutional Neural Networks for Sentence Classification. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, 25\u201329 October 2014, Association for Computational Linguistics.","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"132498","DOI":"10.1016\/j.neucom.2025.132498","article-title":"A differentiable and uncertainty-aware mutual information regularizer for bias mitigation","volume":"669","author":"Incremona","year":"2026","journal-title":"Neurocomputing"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/5\/408\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T14:40:00Z","timestamp":1777041600000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/5\/408"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,24]]},"references-count":33,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["info17050408"],"URL":"https:\/\/doi.org\/10.3390\/info17050408","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,24]]}}}