Authors : Tinakaran Chinnachamy

Volume/Issue : Volume 10 - 2025, Issue 7 - July

Google Scholar : https://tinyurl.com/4dzmkt4t

Scribd : https://tinyurl.com/5dzmfty5

DOI : https://doi.org/10.38124/ijisrt/25jul1787

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : The rapid proliferation of Generative AI (GenAI) technologies has introduced a new era of content creation, automation, and intelligence augmentation. However, the growing reliance on prompt-based interfaces within these models has surfaced critical concerns related to prompt injection, data leakage, adversarial manipulation, and regulatory non- compliance. Despite advancements in large language models (LLMs), the absence of standardized and secure prompt engineering frameworks leaves a vulnerability gap—especially in high-stakes and regulated domains such as healthcare, law, finance, and government operations. This research proposes PromptSecure, a comprehensive protocol-driven framework that introduces secure, context-aware, and auditable prompt engineering methodologies designed for GenAI deployments in regulated environments. Unlike traditional prompt tuning approaches that prioritize model performance, PromptSecure integrates principles from cybersecurity, differential privacy, and software verification to construct a hardened prompt lifecycle—from design and sanitization to execution and monitoring. The protocol encapsulates both static and dynamic prompt validation mechanisms, role-based access control for sensitive prompt execution, and traceable prompt history management using secure audit trails. PromptSecure also incorporates a layered compliance scaffold tailored to conform with GDPR, HIPAA, ISO/IEC 27001, and other global AI governance directives. Experimental evaluation within sandboxed enterprise-grade GenAI environments demonstrates PromptSecure’s capability to mitigate injection risks, enforce prompt boundaries, and retain system integrity under adversarial probing. This study fills a critical research gap at the intersection of prompt engineering and AI governance, and lays the groundwork for establishing secure-by-design GenAI practices essential for building public trust and institutional adoption of foundation models.

Keywords : Secure Prompt Engineering, Generative AI Security, Regulated GenAI Environments, Prompt Injection Defense, Trust- Based Prompt Execution, Language Model Compliance.

References :

1. Baier, C., Hartmann, E., & Moser, R. (2008).  Strategic  alignment  and purchasing efficacy: an exploratory  analysis of their impact on financial performance. Journal of Supply Chain Management, 44(4), 36-52.
2. Brown,  T.,  Mann,  B., Ryder,  N., Subbiah,  M.,  Kaplan,  J.,  Dhariwal,  P.,  Neelakantan,  A.,  Shyam,  P.,  Sastry,  G., Askell, A.,  Agarwal,  S.,  Herbert-Voss,  A., Krueger,  G.,  Henighan,  T.,  Child, R.,  Ramesh,  A., Ziegler,  D. M.,  Wu,  J.,  Winter,  C.,  .  .  .  Amodei,  D.  (2020). Language  Models are  Few-Shot Learners.  Advances  in Neural Information Processing Systems 33.
3. Brynjolfsson, E., Li, D., & Raymond, L. R. (2023). Generative AI at Work.  Buchholz,  K.  (2023).  Threads  Shoots  Past  One  Million  User  Mark  at  Lightning  Speed. https://www.statista.com/chart/29174/time-to-one-million-users/
4. Busch,  K.,  Rochlitzer,  A.,  Sola,  D.,  &  Leopold,  H.  (2023).  Just  tell me:  prompt  engineering  in business  process management. In: arxiv. Chen,  B.,  Zhang, Z.,  Langrené,  N.,  &  Zhu,  S.  (2023).  Unleashing  the  potential of  prompt  engineering  in  Large Language Models: a comprehensive review.
5. arXiv preprint arXiv:2310.14735.  Chui, M., Roberts, R., Rodchenko, T., Singla, A., Sukharevsky, A., Yee, L., & Zurkiya, D. (2023). What every CEO should know about generative AI.
6. Clavié, B., Ciceu, A., Naylor, F., Soulié, G., & Brightwell, T. (2023). Large Language Models in the Workplace: A Case  Study  on  Prompt  Engineering  for  Job  Type  Classification.  In  Natural  Language  Processing  and Information Systems (pp. 3-17). Springer.
7. Dang,  H.,  Mecke,  L.,  Lehmann,  F.,  Goller,  S.,  &  Buschek,  D.  (2022).  How  to  Prompt?  Opportunities  and Challenges  of  Zero-  and  Few-Shot  Learning  for  Human-AI  Interaction  in  Creative  Applications  of Generative Models ACM CHI Conference on Human Factors in Computing Systems, New Orleans, USA.
8. Dwivedi, Y. K., Kshetri, N., Hughes, L., & authors), e. a. m. (2023). Opinion Paper: “So what if ChatGPT wrote it?” Multidisciplinary  perspectives  on  opportunities, challenges  and implications  of generative  conversational AI for research, practice and polic. International Journal of Information Management, 71(102642).
9. Foster,  D.  (2019).  Generative  Deep  Learning:  Teaching  Machines  to  Paint,  Write,  Compose  and  Play (2  ed.). O’Reily Media.  Garcia-Penalvo, F., & Vazquez-Ingelmo, A. (2023).  What Do We Mean by GenAI? A Systematic Mapping of The Evolution,  Trends,  and  Techniques  Involved  in  Generative  AI.  International  Journal  of  Interactive Multimedia and Artificial Intelligence, 8(4), 7-16.
10. Joshi,  A.  V.  (2019).  Machine  Learning  and  Artificial  Intelligence.  Springer. https://doi.org/https://doi.org/10.1007/978-3-030-26622-6  Jovanovic,  M.,  &  Campbell,  M.  (2022).  Generative  Artificial  Intelligence:  Trends  and  Prospects.  Computer, 55, 107-112.
11. Lester,  B.,  Al-Rfou, R.,  &  Constant,  N.  (2021). The  power  of  scale for  parameter-efficient  prompt  tuning. arXiv preprint arXiv:2104.08691.  Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023). Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing. ACM Computing Surveys, 55(9).
12. Liu, X., Zheng, Y., Du, Z., Ding, M., Qian, Y., Yang, Z., & Tang, J. (2023). GPT understands, too. AI Open.  Mayring, P. (2014). Qualitative content analysis: theoretical foundation, basic procedures and software solution.
13. Micus,  C.,  Weber,  M.,  Böttcher,  T.,  Böhm,  M.,  &  Krcmar,  H.  (2023).  Data-Driven  Transformation  in  the Automotive Industry: The Role of Customer Usage Data in Product Development.
14. Mishra, S.,  Khashabi,  D., Baral, C.,  Choi,  Y., & Hajishirzi,  H.  (2021). Reframing Instructional Prompts to  GPTk's Language. arXiv preprint arXiv:2109.07830.
15. Monczka,  R.  M.,  Handfield,  R.  B.,  Giunipero,  L.  C.,  &  Patterson,  J.  L.  (2009).  Purchasing  and  Supply  Chain Management.
16. Ooi, K.-B., Tan, G. W.-H., Al-Emran, M., Al-Sharafi, M. A., Capatina, A., Chakraborty, A., Dwivedi, Y. K., Huang, T.-L.,  Kar,  A.  K.,  &  Lee,  V.-H.  (2023).  The  potential  of  Generative  Artificial  Intelligence  across disciplines: Perspectives and future directions. Journal of Computer Information Systems, 1-32.
17. Ouyan, L.,  Wu,  J.,  Jiang,  X., Almeida,  D., Wainwright,  C. L.,  Mishkin,  P.,  Zhang,  C., Agarwal,  S., Slama,  K.,  & Ray, A. (2022). Training language models to follow instructions with human feedback.  Porter, M. E. (1985). Competitive advantage: Creating and sustaining superior performance. Free Press.
18. Radford,  A.,  Narasmhan,  K.,  Salimans,  T.,  &  Sutskever,  I.  (2018).  Improving  Language  Understanding  by Generative Pre-Training.  Raj, R., Singh, A., Kumar, V., & Verma, P. (2023). Analyzing the potential benefits and use cases of ChatGPT as a tool for  improving  the  efficiency  and  effectiveness of business operations. BenchCouncil Transactions  on Benchmarks, Standards and Evaluations, 3(3), 100140.
19. Rane,  N.  (2023).  Role  and  challenges  of  ChatGPT  and  similar  generative  artificial  intelligence  in  business management. Available at SSRN 4603227.  Santu, S.  K.  K., &  Feng,  D.  (2023).  TELeR:  A  General  Taxonomy of  LLM  Prompts  for Benchmarking  Complex Tasks. arXiv preprint arXiv:2305.11430.
20. Shanahan, M., McDonell, K., & Reynolds, L. (2023). Role play with large language models. Nature, 1-6.  Tredinnick,  L.,  &  Laybats,  C.  (2023).  Black-box  creativity  and  generative  artifical  intelligence.  Business Information Review, 40(3), 98-102. https://doi.org/10.1177/02663821231195131  van Weele, A. J. (2010). Purchasing and Supply Chain Management: Analysis, Strategy, Planning and Practice.
21. Wang, L., Xu, Z., & Iwaihara, M. Soft and Hard Prompting for Document Classification with Only Label Names.  Wei, J.,  Wang,  X., Schuurmans,  D., Bosma,  M., Xia,  F.,  Chi, E.,  Le,  Q. V., &  Zhou,  D. (2022).  Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824-24837.
22. White,  J.,  Fu,  Q.,  Hays,  S., Sandborn,  M., Olea,  C.,  Gilbert,  H., Elnashar,  A., Spencer-Smith,  J., &  Schmidt, D. (2023). A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT.  Yin, R. K. (2018). Case study research and applications (Vol. 6). Sage Thousand Oaks, CA.