Investigating Information Security Challenges in AI-Powered Bots: A Literature Review

Crossmark - Check for updates

Authors

DOI:

https://doi.org/10.68033/ijaimda.1.1.51-55

Keywords:

AI-Powered Chatbots, Privacy Concerns, Cybersecurity, Adversarial Attacks, Threat Intelligence, Regulatory Frameworks

Abstract

AI-driven service bots have become game-changing technologies in various sectors, including cybersecurity, healthcare, and customer service. Their increasing adoption comes with complex information security issues, such as privacy risks, adversarial vulnerabilities, data protection gaps, and regulatory compliance issues. To investigate these issues and evaluate design approaches for safe and reliable AI bot systems, this literature review summarizes various recent studies conducted between the year 2021 and 2025. User privacy, adversarial threats, cybersecurity frameworks, AI-enhanced threat intelligence, and privacy-aware system design are among the thematic areas into which the review divides the studies. With suggestions for further research focusing on strong, scalable, and explicable security mechanisms in AI-driven bots, gaps in regulatory alignment, empirical testing, and interdisciplinary integration are noted.

References

[1] Admass, W. S., Munaye, Y. Y., & Diro, A. A. (2024). Cyber security: State of the art, challenges and future directions. Cyber Security and Applications, 2, 100031.

[2] Akhtar, Z. B., & Rawol, A. T. (2024). Enhancing cybersecurity through AI-powered security mechanisms. IT Journal Research and Development, 9(1), 50-67.

[3] Alturkistani, H., & Chuprat, S. (2024). Artificial Intelligence and Large Language Models in Advancing Cyber Threat Intelligence: A Systematic Literature Review. DOI:10.21203/rs.3.rs-5423193/v1

[4] Alawadhi, S. A., Zowayed, A., Abdulla, H., Khder, M. A., & Ali, B. J. (2022, June). Impact of artificial intelligence on information security in business. In 2022 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS) (pp. 437-442). IEEE.

[5] Biswas, A. A., Zulfiker, M. S., Rahman, M. M., Jani, M. R., & Anwar, M. M. (2025, March). Data Privacy and Security Analysis for Mental Health Chatbot Applications. In 2025 20th ACM/IEEE International Conference on Human-Robot Interaction (HRI) (pp. 1245-1249). IEEE

[6] Binhammad, M., Alqaydi, S., Othman, A., & Abuljadayel, L. H. (2024). The role of AI in cyber security: Safeguarding digital identity. Journal of Information Security, 15(2), 245-278.

[7] Boucher, N., Shumailov, I., Anderson, R., & Papernot, N. (2022, May). Bad characters: Imperceptible nlp attacks. In 2022 IEEE Symposium on Security and Privacy (SP) (pp. 1987-2004). IEEE.

[8] Dev, J. (2022). Privacy-preserving conversational interfaces. Indiana University.

[9] Gumusel, E. (2025). A literature review of user privacy concerns in conversational chatbots: A social informatics approach: An Annual Review of Information Science and Technology (ARIST) paper. Journal of the Association for Information Science and Technology, 76(1), 121-154.

[10] Kumar, D. A., Sharif, S. M., & Aravind, T. (2024, October). Development and Implementation of a Secure Document Analysis and Chatbot System for Context-Aware User Interactionsr. In 2024 Global Conference on Communications and Information Technologies (GCCIT) (pp. 1-6). IEEE.

[11] Liew, L. S., Sabaliauskaite, G., Kandasamy, N. K., & Wong, C. Y. W. (2021, December). A novel system-theoretic matrix-based approach to analysing safety and security of cyber-physical systems. In Telecom (Vol. 2, No. 4, pp. 536-553). MDPI.

[12] Nacheva, R., & Azeroual, O. (2024, November). Security of AI-Powered Systems: Threat Intelligence on the Edge. In 2024 8th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) (pp. 1-6). IEEE.

[13] Silva, G. R. S., & Canedo, E. D. (2025). Privacy in Chatbot Conversation-Driven Development: A Comprehensive Review and Requirements Proposal. ACM Transactions on Software Engineering and Methodology.

[14] Tidjon, L. N., & Khomh, F. (2022). Threat assessment in machine learning based systems. arXiv preprint arXiv:2207.00091.

Downloads

Published

2026-06-22

How to Cite

Investigating Information Security Challenges in AI-Powered Bots: A Literature Review. (2026). International Journal of Artificial Intelligence, Machine Learning and Data Analytics, 1(1), 51-55. https://doi.org/10.68033/ijaimda.1.1.51-55