Tejas Kolhe,
Onkar Thorat,
Rutuja Urunkar,
Ajay Pachore,
Yogesh Khandekar,
Ajay Gawali,
- Student, Department of Electronics and Computer Engineering, Pune University, Maharashtra, India
- Student, Department of Electronics and Computer Engineering, Pune University, Maharashtra, India
- Student, Department of Electronics and Computer Engineering, Pune University, Maharashtra, India
- Student, Department of Electronics and Computer Engineering, Pune University, Maharashtra, India
- Assistant Professor, Department of Electronics and Computer Engineering, Pune University, Maharashtra, India
- Student, Department of Electronics and Computer Engineering, Pune University, Maharashtra, India
Abstract
The need for defense systems that are smarter, faster, and more adaptable has never been greater in an era when cyber threats are becoming increasingly intelligent and evasive. This project presents a cutting-edge approach to cybersecurity through the synergistic fusion of Artificial Intelligence (AI) and Machine Learning (ML), aiming not just to detect threats—but to predict and prevent them proactively. The automated ingestion of various cybersecurity data, including live network traffic, behavioral logs, and threat intelligence feeds, sets the stage for the working flow. further, this data is pass via pipeline for preprocessing, in which it get cleaned, get organized and added with contextual metadata. key threat are. removed using data manipulation and selection method, which make data ready for advanced analytics after that the ready data is analyzed by a machine learning algorithms, these algorithms are not fixed , they are adapt themselves according to emerging threats.AI-based correlation engine consolidate results, removes noise, and raises only high-confidence threats for review. .In the end of the day, the system allows security teams to respond aggressively and swiftly through dynamic dashboards as well as automated alerts with real-time threat information. Through this smart and proactive framework, the project significantly improves modern threat intelligence by achieving greater threat visibility, quicker response, and an appreciable decrease in false positives.
Keywords: Cybersecurity, threat intelligence, artificial intelligence, machine learning, proactive threat detection
[This article belongs to Journal of Artificial Intelligence Research & Advances ]
References
- Rieder B. engines of order: a mechanology of algorithmic techniques. 1st ed. London: Routledge; 2020. doi:10.5117/9789462986190.
- Boglaev I. a numerical method for solving nonlinear integra-differential equations of Fredholm type. journal of computational mathematics. 2016;34(3):262-284.
- Alaskar H. profound learning approaches for interruption location in IoT organizations. 2021.
- Dayyabu YY. the use of artificial intelligence techniques in credit card fraud detection: a quantitative study. 2023.
- Hasan MR, Ferdous J. prevalence of artificial intelligence and machine learning strategies in hybrid film recommendation systems. 2024.
- Chigurupati M, Malviya RK, Toorpu AR, Anand K. ai agents for cloud reliability: autonomous threat detection and mitigation aligned with site reliability engineering principles. in: 2025 ieee 4th international conference on ai in cybersecurity (ICAIC). Houston, tx; 2025. p. 1-4. doi:10.1109/icaic63015.2025.10849322.
- Nallapareddy VSSRN, Katta SKR. ai-enhanced cyber security proactive threat detection and response systems. in: 2025 4th international conference on sentiment analysis and deep learning (ICSADL). Bhimdatta, Nepal; 2025. p. 1510-1514. doi:10.1109/icsadl65848.2025.10933436.
- Gujar SS. optimizing threat mitigation in critical infrastructure through ai-driven cybersecurity solutions. in: 2024 global conference on communications and information technologies (GCCIT). Bangalore, India; 2024. p. 1-7. doi:10.1109/gccit63234.2024.10862689.
- Kumar A, Guleria K. mitigating adversarial threats: safeguarding ai-driven fraud detection systems against malicious exploits. in: 2024 4th international conference on advancement in electronics & communication engineering (AECE). Ghaziabad, India; 2024. p. 736-740. doi:10.1109/aece62803.2024.10911168.
- Dhanushkodi K, Thejas S. ai-enabled threat detection: leveraging artificial intelligence for advanced security and cyber threat mitigation. IEEE access. 2024;12:173127-173136. doi:10.1109/access.2024.3493957.
- Prabu K, et al. enhancing cloud security with ai-driven anomaly detection for zero-day threats. in: 2024 1st international conference on advances in computing, communication and networking (ICAC2N). Greater Noida, India; 2024. p. 1087-1092. doi:10.1109/icac2n63387.2024.10895696.
- Surya S, et al. ai-driven threat detection: implementing multi-layer security networks in cloud environments. in: 2025 international conference on pervasive computational technologies (ICPCT). Greater Noida, India; 2025. p. 465-470. doi:10.1109/icpct64145.2025.10941038.
- Rathor K, et al. temporal threat recognition in supply chains: integrating hidden markov models for proactive security with ai-driven automated threat hunting. in: 2024 international conference on advances in modern age technologies for health and engineering science (Amathe). Shivamogga, India; 2024. p. 1-6. doi:10.1109/amathe61652.2024.10582202.
- Prabha M, et al. ai-driven cyber threat detection: revolutionizing security frameworks in management information systems. in: 2024 international conference on intelligent cybernetics technology & applications (ICICYTA). Bali, Indonesia; 2024. p. 357-362. doi:10.1109/
2024.10912927.
Journal of Artificial Intelligence Research & Advances
| Volume | 13 | |
| Issue | 02 | |
| Received | 20/02/2026 | |
| Accepted | 11/05/2026 | |
| Published | 15/05/2026 | |
| Publication Time | 84 Days |