Agentic AI for Cybersecurity and Risk Management (Autonomous AI for Fraud Detection, Compliance, And Threat Mitigations)

References

[1] Akhunzada, A., Al-Shamayleh, A. S., Zeadally, S., Almogren, A., & Abu-Shareha, A. A. (2024). Design and performance of an AI-enabled threat intelligence framework for IoT-enabled autonomous vehicles. Computers and Electrical Engineering, 119, 109609.https://doi.org/10.1016/j.compeleceng.2024.109609

[2] Abu-Hakima, S., Toloo, M., & White, T. (1997, July). A multi-agent systems approach for fraud detection in personal communication systems. In Proceedings of the Fourteenth National Conference on Artificial Intelligence (AAAI-97) (pp. 1-8).

[3] Acharya, D. B., Kuppan, K., & Divya, B. (2025). Agentic AI: Autonomous Intelligence for Complex Goals–A Comprehensive Survey. IEEE Access.https://doi.org/10.1109/ACCESS.2025.3532853

[4] Butler, T., & O’Brien, L. (2019). Artificial intelligence for regulatory compliance: Are we there yet?. Journal of Financial Compliance, 3(1), 44-59.

[5] Boosa, S. (2024). AI-POWERED RISK MANAGEMENT IN FINTECH: LEVERAGING BIG DATA FOR FRAUD DETECTION. International Journal of Science and Engineering, 10(3), 77-88. https://doi.org/10.53555/ephijse.v10i3.262

[6] Bello, O. A., Ogundipe, A., Mohammed, D., Adebola, F., & Alonge, O. A. (2023). AI-Driven Approaches for real-time fraud detection in US financial transactions: challenges and opportunities. European Journal of Computer Science and Information Technology, 11(6), 84-102.

[7] Balakrishnan, A. (2024). Leveraging artificial intelligence for enhancing regulatory compliance in the financial sector. International Journal of Computer Trends and Technology. https://ssrn.com/abstract=4842699

[8] Cholakov, G., & Stoyanova-Doycheva, A. (2024). Extending Fraud Detection in Students Exams Using AI. TEM Journal, 13(4), 3068.

[9] Deshpande, A. (2024, April). Regulatory Compliance and AI: Navigating the Legal and Regulatory Challenges of AI in Finance. In 2024 International Conference on Knowledge Engineering and Communication Systems (ICKECS) (Vol. 1, pp. 1-5). IEEE.https://doi.org/10.1109/ICKECS61492.2024.10616752

[10] Elahi, H., Wang, G., Xu, Y., Castiglione, A., Yan, Q., & Shehzad, M. N. (2021). On the characterization and risk assessment of ai-powered mobile cloud applications. Computer Standards & Interfaces, 78, 103538.https://doi.org/10.1016/j.csi.2021.103538

[11] Faisal, N. A., Nahar, J., Sultana, N., & Mintoo, A. A. (2024). Fraud Detection in Banking Leveraging Ai to Identify and Prevent Fraudulent Activities in Real-Time. Journal of Machine Learning, Data Engineering and Data Science, 1(01), 181-197.

[12] Folorunso, A., Adewumi, T., Adewa, A., Okonkwo, R., & Olawumi, T. N. (2024). Impact of AI on cybersecurity and security compliance. Global Journal of Engineering and Technology Advances, 21(01), 167-184.

[13] Fouad, N. S. (2022). The non-anthropocentric informational agents: Codes, software, and the logic of emergence in cybersecurity. Review of International Studies, 48(4), 766-785.https://doi.org/10.1017/S0260210521000681

[14] Fountaine, T., McCarthy, B., & Saleh, T. (2019). Building the AI-powered organization. Harvard business review, 97(4), 62-73.

[15] Hernández-Rivas, A., Morales-Rocha, V., & Sánchez-Solís, J. P. (2024). Towards autonomous cybersecurity: A comparative analysis of agnostic and hybrid AI approaches for advanced persistent threat detection. In Innovative Applications of Artificial Neural Networks to Data Analytics and Signal Processing (pp. 181-219). Springer, Cham. https://doi.org/10.1007/978-3-031-69769-2_8

[16] Kshetri, N. Transforming Cybersecurity with Agentic Ai to Combat Emerging Cyber Threats. Available at SSRN 5159598. https://dx.doi.org/10.2139/ssrn.5159598

[17] Khan, R., Sarkar, S., Mahata, S. K., & Jose, E. (2024). Security Threats in Agentic AI System. arXiv preprint arXiv:2410.14728. https://doi.org/10.48550/arXiv.2410.14728

[18] Koppolu, H. K. R. Deep Learning and Agentic AI for Automated Payment Fraud Detection: Enhancing Merchant Services Through Predictive Intelligence.

[19] Kavitha, D., & Thejas, S. (2024). Ai enabled threat detection: Leveraging artificial intelligence for advanced security and cyber threat mitigation. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3493957

[20] Luo, B., Zhang, Z., Wang, Q., Ke, A., Lu, S., & He, B. (2024). Ai-powered fraud detection in decentralized finance: A project life cycle perspective. ACM Computing Surveys, 57(4), 1-38. https://doi.org/10.1145/3705296

[21] Lim, H. Y. F. (2022). Regulatory compliance. In Artificial Intelligence (pp. 85-108). Edward Elgar Publishing.https://doi.org/10.4337/9781800371729

[22] Mustafa, F., & Sharif, F. (2024). The Future of AI in Network Security: Autonomous Threat Hunting and Response Systems.

[23] Oesch, S., Hutchins, J., Austria, P., & Chaulagain, A. (2025). Agentic AI and the Cyber Arms Race. arXiv preprint arXiv:2503.04760. https://doi.org/10.48550/arXiv.2503.04760

[24] Paul, R. K., & Nandy, S. (2020). AI-POWERED FINANCIAL TECHNOLOGY FOR IMPROVED INVESTMENT DECISION-MAKING AND RISK MANAGEMENT. INTERNATIONAL JOURNAL OF ACCOUNTING AND FINANCIAL MANAGEMENT RESEARCH AND DEVELOPMENT (IJAFMRD), 1(2), 1-18.

[25] Padmanaban, H. (2024). Revolutionizing regulatory reporting through AI/ML: Approaches for enhanced compliance and efficiency. Journal of Artificial Intelligence General science (JAIGS) ISSN: 3006-4023, 2(1), 71-90. https://doi.org/10.60087/jaigs.v2i1.98

[26] Patial, A. (2023). AI-powered banking: From customer service to risk management.

[27] Rashid, S. Z. U., Montasir, I., Haq, A., Ahmmed, M. T., & Alam, M. M. Securing Agentic AI: Threats, Risks and Mitigation.

[28] Rauf, M. A., & Jim, M. M. I. (2024). AI-Powered Predictive Analytics for Intellectual Property Risk Management in Supply Chain Operations: A Big Data Approach. Global Mainstream Journal, 1(4), 10-62304. https://dx.doi.org/10.62304/ijse.v1i04.184

[29] Prodromidis, A. L., & Stolfo, S. J. (1999). Agent-based distributed learning applied to fraud detection. In Sixteenth National Conference on Artificial Intelligence.

[30] Sindiramutty, S. R. (2023). Autonomous threat hunting: A future paradigm for AI-driven threat intelligence. arXiv preprint arXiv:2401.00286. https://doi.org/10.48550/arXiv.2401.00286

[31] Soundenkar, S., Bhosale, K., Jakhete, M. D., Kadam, K., Chowdary, V. G. R., & Durga, H. K. (2024). AI Powered Risk Management: Addressing Cybersecurity Threats in Financial Systems. Library of Progress-Library Science, Information Technology & Computer, 44(3).

[32] Tallam, K. (2025). Transforming Cyber Defense: Harnessing Agentic and Frontier AI for Proactive, Ethical Threat Intelligence. arXiv preprint arXiv:2503.00164. https://doi.org/10.48550/arXiv.2503.00164

[33] Tripathi, P. M. (2025). Impact of AI on Regulatory Compliance in Information Security. International Journal of Computer Engineering and Technology (IJCET), 16(1).

[34] Wang, B. X., Chen, J. L., & Yu, C. L. (2022). An AI-powered network threat detection system. IEEE Access, 10, 54029-54037. https://doi.org/10.1109/ACCESS.2022.3175886

[35] Wasif, N. (2022). Cybersecurity in Autonomous Vehicles: AI-Based Threat Detection and Response Mechanisms.

[36] Yigit, Y., Ferrag, M. A., Ghanem, M. C., Sarker, I. H., Maglaras, L. A., Chrysoulas, C., ... & Janicke, H. (2025). Generative AI and LLMs for critical infrastructure protection: evaluation benchmarks, agentic AI, challenges, and opportunities. Sensors, 25(6), 1666. https://doi.org/10.3390/s25061666

@article{1707702,
      author = {Sai Santhosh Polagani},
      title = {Agentic AI for Cybersecurity and Risk Management (Autonomous AI for Fraud Detection, Compliance, And Threat Mitigations)},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {8},
      number = {10},
      pages = {3-20},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1707702.pdf},
      abstract = {The high complexity of cyber threats prompts Agentic AI systems to restructure cybersecurity measures because they autonomously handle self-directed decisions. Agentic AI receives its capability for real-time cyber threat detection and analysis and response through deep learning and machine learning combined with reinforcement learning. This enables automatic response instead of human-based detection and intervention methods. Such security systems use automated threat assessment with abnormality detection to enable self-operated incident response functions and accelerate defense against fraud and compliance violations. Current financial institutions utilize Agentic AI technology to develop operational fraud detection systems as their primary beneficial application. Machine agents during transactions execute behavioral analysis and predictive analysis to find fraudulent activities through organizational data patterns. Self-operated security auditing through Agentic AI enhances regulatory compliance while simultaneously facilitating easier manual audit tasks to support data protection standards. The implementation of Agentic AI brings value to businesses through multiple benefits but introduces three main operational difficulties due to operational biases and unclear decision paths as well as security risk exposure. AI autonomous security systems need ethical methods to achieve critical decisions before they can provide users with secure and unbiased cybersecurity services. The document explores Agentic AI applications in cybersecurity and fraud detection with an analysis of both advantages and challenges in addition to expected future application prospects.},
      keywords = {Agentic AI in Cybersecurity, Autonomous AI for Threat Detection, AI-Powered Risk Management, Fraud Detection with AI Agents, AI in Compliance and Regulatory Security},
      month = {April},
  }