The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Secure Pipelines, Smarter AI: LLM-Powered Data Engineering for Threat Detection and Compliance
Open accessAbstract
As digital ecosystems become increasingly complex, safeguarding sensitive data while ensuring regulatory compliance poses a dual challenge. Traditional security systems often fall short in detecting nuanced threats or adapting to evolving attack vectors. In contrast, large language models (LLMs) offer a transformative approach—enabling intelligent threat detection through contextual analysis, anomaly interpretation, and adaptive rule learning. This paper proposes a hybrid data engineering framework that integrates LLMs into secure pipelines for real-time threat monitoring, compliance enforcement, and operational governance. We explore architectural models, performance benchmarks, and use cases demonstrating how LLMs elevate both security posture and auditability. Through comparative analysis and flow-based design, we highlight the future of resilient, AI-driven data engineering tailored for modern cybersecurity demands.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Many LLM-only frameworks do not offer auditability and verifiability.
“but many LLM-only frameworks do not offer them [6].”
From The Evolution of Agentic AI in Cybersecurity: From Single LLM Reasoners to Multi-Agent Systems and Autonomous Pipelines (2026) · cites this paper as [6]
The Introduction (page unavailable) identifies auditability as a challenge when integrating LLMs into secure pipelines, and Section 5 describes symbolic validators as making actions traceable and policy-aligned. The paper does not establish that many LLM-only frameworks lack both auditability and verifiability. (LLM, conf=0.82)
Experimental — accuracy not yet measuredAuditability and verifiability are critical for deploying in a SOC context with regulatory/compliance requirements.
“To deploy in a SOC context with regulatory/compliance requirements, auditability, and verifiability are critical”
From The Evolution of Agentic AI in Cybersecurity: From Single LLM Reasoners to Multi-Agent Systems and Autonomous Pipelines (2026) · cites this paper as [6]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Software developers' perceptions of productivity
Meyer, A. N., Fritz, T., Murphy, G. C., & Zimmermann, T. (2014) · Proceedings of the 22nd ACM SIGSOFT International Symposium on Foundations of Software Engineering · doi:10.1145/2635868.2635892 · Cited by 224
Flagged first, then by citations
Research works printed but not linked: 20
- Koziolek, H.; Burger, A. Rule-based Code Generation in Industrial Settings: Four Case Studies. In Proceedings of the Proceedings of the 29th Annual ACM Symposium on Applied Computing. ACM, 2014, pp. 1234-1241. https://doi.org/10.1145/2591062.2591072. · DOI
- Zhang, Y.; Li, Y.; Wang, S.; Zou, X. Transformers for Natural Language Processing: A Comprehensive Survey. arXiv preprint arXiv:2305.13504 2023. · arXiv
- Wang, Z.; Xue, Y.; Dong, Y. A Systematic Review of Rule-Based Systems in Modern Software Architecture. Journal of Systems Architecture 2024, 103, 103193. https://doi.org/10.1016/j.sysarc.2024.103193. · DOI
- Feng, Z.; Guo, D.; Tang, D.; Duan, N.; Feng. CodeBERT: A Pre-Trained Model for Programming and Natural Languages. arXiv preprint arXiv:2002.08155 2020. · arXiv
- Bollikonda, M. Hybrid Reasoning in AI: Integrating Rule-Based Systems with Transformer Models. Preprints 2025. Preprint, available at Preprints.org, https://doi.org/10.20944/preprints202504.0887.v1. · DOI
- Bura, C. ENRIQ: Enterprise Neural Retrieval and Intelligent Querying. REDAY -Journal of Artificial Intelligence & Computational Science 2025. https://doi.org/10.5281/zenodo.14737182. · DOI
- Bura, C.; Jonnalagadda, A.K.; Naayini, P. The Role of Explainable AI (XAI) in Trust and Adoption. Journal of Artificial Intelligence General science (JAIGS) ISSN: 3006-4023 2024, 7, 262-277.
- Kamatala, S.; Jonnalagadda, A.K.; Naayini, P. Transformers Beyond NLP: Expanding Horizons in Machine Learning. Iconic Research And Engineering Journals 2025, 8. https://doi.org/https://www.irejournals.com/ paper-details/1706957.
- Wang, Y.; Liu, W.; Liu, G.; Du, X.; Zhang, Y.; Sun, S.; Li, L. CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation. In Proceedings of the Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021, pp. 8696-8708.
- Zheng, Q.; Xia, X.; Zou, X.; Dong, Y.; Wang, S.; Xue, Y.; Wang, Z.; Shen, L.; Wang, A.; Li, Y.; et al. Codegeex: A Pre-trained Model for Code Generation with Multilingual Evaluations on HumanEval-X. arXiv preprint arXiv:2303.17568 2023. · arXiv
- Kamatala, S.; Naayini, P.; Myakala, P.K. Mitigating Bias in AI: A Framework for Ethical and Fair Machine Learning Models. Available at SSRN 5138366 2025.
- Myakala, P.K.; Jonnalagadda, A.K.; Bura, C. Federated Learning and Data Privacy: A Review of Challenges and Opportunities. International Journal of Research Publication and Reviews 2024, 5. https://doi.org/10.55248 /gengpi.5.1224.3512. · DOI
- Wangoo, D.P. Artificial Intelligence Techniques in Software Engineering for Automated Software Reuse and Design. In Proceedings of the 2018 4th International Conference on Computing Communication and Automation (ICCCA), 2018, pp. 1-4. https://doi.org/10.1109/CCAA.2018.8777584. · DOI
- Ahmad, W.U.; Chakraborty, S.; Ray, B.; Chang, K.W. Unified Pre-training for Program Understanding and Generation. arXiv preprint arXiv:2103.06333 2021. · arXiv
- Nijkamp, E.; Lee, B.P.; Pang, R.; Zhou, S.; Xiong, C.; Savarese, S.; Ni, J.; Keutzer, K.; Zou, Y. CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis. arXiv preprint arXiv:2203.13474 2022. · arXiv
- Lu, S.; Guo, D.; Ren, S.; Huang, J.; Svyatkovskiy, A. CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation, 2021, [arXiv:cs.SE/2102.04664].
- Kamatala, S. AI Agents And LLMS Revolutionizing The Future Of Intelligent Systems. International Journal of Scientific Research and Engineering Development 2024, 7. https://doi.org/10.2139/ssrn.5118607. · DOI
- Myakala, P.K. Beyond Accuracy: A Multi-faceted Evaluation Framework for Real-World AI Agents. Interna- tional Journal of Scientific Research and Engineering Development 2024, 7. https://doi.org/10.5281/zenodo.1488 0716. · DOI
- Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A.N.; Kaiser, L.; Polosukhin, I. Attention is All You Need. In Proceedings of the Advances in Neural Information Processing Systems, 2017, Vol. 30.
- Le, H.; Wang, Y.; Gotmare, A.D.; Savarese, S.; Hoi, S. OpenReview: A Platform for Transparent and Open Peer Review. In Proceedings of the OpenReview, 2023.
Cited by
Sorted by citations
Vinay, V. (2026) · 2026 IEEE 5th International Conference on AI in Cybersecurity (ICAIC) · doi:10.1109/icaic67076.2026.11395809 · Cited by 15
Metadata
- Authors
- Bollikonda, M., & Bollikonda, T.
- Corresponding author
- Bollikonda, Manaswini
- Venue
- Preprints.org
- Publisher
- MDPI AG
- Published
- 2025-04-16
- OpenAlex
- W4409587840
- Cited by
- 1
- References
- 1
- Citations by year
- 2026: 1
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Locations
- Preprints.org (acceptedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Keywords
- large language models, data engineering pipelines, threat detection, regulatory compliance, real-time threat monitoring, compliance enforcement, anomaly detection, auditability, cybersecurity
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
