Citation :

Sivamurugan Perumal, "Artificial Intelligence: Leveraging Privacy and Security on AI Models and Small Language Model Thrive," International Journal of Computer Trends and Technology (IJCTT), vol. 74, no. 3, pp. 1-6, 2026. Crossref, https://doi.org/10.14445/22312803/IJCTT-V74I3P101

Abstract

Today, we are in a rapid technological growth with artificial intelligence, in which privacy and security are the primary concerns. With various language models in the current market, the data that models are trained to provide relevant detail responses plays a vital role in how privacy and security can be leveraged without compromising, for example, the data like Personal Identifiable Information (PI2) [1] and Health Insurance Portability and Accountability ACT (HIPAA) [2]. In this, we provide a review of privacy and security that can be implemented in small industries (specific to the domain) with a Small Language Model (SLM). It also suggests which models are available on the market and how they can be leveraged, considering common factors that align with their business affordability.

Keywords

Artificial Intelligence, Cost savings, Computing, Financial firms, HealthCare, SLM (Small Language Model).

References

[1] Nicholas Carlini et al., “Extracting Training Data from Large Language Models,” Proceedings of the 30^th USENIX Security Symposium (USENIX Security’21), 2021.
[Google Scholar] [Publisher Link]

[2] Vivying S.Y. Cheng, and Patrick C.K. Hung, “Health Insurance Portability and Accountability Act (HIPPA) Compliant Access Control Model for Web Services,” International Journal of Healthcare Information Systems and Informatics, vol. 1, no, 1, 2006.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Arthur Jochems et al., “Developing and Validating a Survival Prediction Model for NSCLC Patients through Distributed Learning Across 3 Countries,” International Journal of Radiation Oncology, Biology, Physics, vol. 99, no. 2, pp. 344-352, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Arthur Jochems et al., “Distributed Learning: Developing a Predictive Model based on Data from Multiple Hospitals without Data Leaving the Hospital- A Real Life Proof of Concept,” Radiotherapy and Oncology, vol. 121, no. 3, pp. 459-467, 2016.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Brendan McMahan et al., “Communication-efficient Learning of Deep Networks from Decentralized Data,” Proceedings of the 20^th International Conference on Artificial Intelligence and Statistics, 2017.
[Google Scholar] [Publisher Link]

[6] Tom Brown et al., “Language Models are Few-shot Learners,” Advances in Neural Information Processing Systems, vol. 33, 2020.
[Google Scholar] [Publisher Link]

[7] Daniel M. Ziegler et al., “Fine-tuning Language Models from Human Preferences,” arXiv preprint arXiv:1909.08593, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Malin Jansson et al., “Online Question and Answer Sessions: How Students Support Their Own and Other Students’ Processes of Inquiry in a Text-based Learning Environment,” The Internet and Higher Education, vol. 51, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Rodrigo Pedro et al., “From Prompt Injections to SQL Injection Attacks: How Protected is your LLM-Integrated Web Application?,” arXiv preprint arXiv:2308.01990, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Matthew Fredrikson et al., “Privacy in Pharmacogenetics: An End-to-end case Study of Personalized Warfarin Dosing,” 23^rd USENIX Security Symposium, 2014.
[Google Scholar] [Publisher Link]

[11] Shuai Zhao et al., “A Survey of Backdoor Attacks and Defenses on Large Language Models: Implications for Security Measure,” Authorea Preprints, pp. 1-21, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Yanzhou Li et al., “BadEdit: Backdooring Large Language Models by Model Editing,” Cryptography and Security, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Vinu Sankar Sadasivan et al., “Fast Adversarial Attacks on Language Models in one GPU Minute,” arXiv preprint, pp. 1-20, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Vyas Raina, Adian Liusie, and Mark Gales, “Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment,” Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 7499-7517, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Siwon Kim et al., “ProPILE: Probing Privacy Leakage in Large Language Models,” Advances in Neural Information Processing Systems, 2023.
[Google Scholar] [Publisher Link]

[16] Niloofar Mireshghallah et al., “Can LLMs Keep a Secret? Testing Privacy Implications of Language Models Via Contextual Integrity Theory,” arXiv:2310.17884, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Ali Naseh et al., “Stealing the Decoding Algorithms of Language Models,” Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, pp. 1835-1849, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Ashwinee Panda et al., “Teach LLMs to Phish: Stealing Private Information from Language Models,” arXiv:2403.00871, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Michael Duan et al., “Do Membership Inference Attacks Work on Large Language Models?,” arXiv:2402.07841, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Robin Staab et al., “Beyond Memorization: Violating Privacy Via Inference with Large Language Models,” arXiv:2310.07298, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Shenao Yan et al., “An LLM-assisted Easy-to-trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection,” 33^rd USENIX Security Symposium, 2024.
[Google Scholar] [Publisher Link]

[22] Manli Shu et al., “On the Exploitability of Instruction Tuning,” Advances in Neural Information Processing Systems, 2023.
[Google Scholar] [Publisher Link]

[23] Zhaohan Xi et al., “Defending Pre-trained Language Models as Few-shot Learners Against Backdoor Attack,” Advances in Neural Information Processing Systems, 2023.
[Google Scholar] [Publisher Link]

[24] Xi Li et al., “Chain-of-scrutiny: Detecting Backdoor Attacks for Large Language Models,” Findings of the Association for Computational Linguistics, pp. 7705-7727, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[25] Xilie Xu et al., “An LLM can Fool Itself: A Prompt-based Adversarial Attack,” arXiv: 2310.13345, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Aounon Kumar et al., “Certifying LLM Safety against Adversarial Prompting,” arXiv: 2309.02705, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[27] Hannah Brown et al., “Self-evaluation as a Defense against Adversarial Attacks on LLMs,” arXiv preprint, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Yukun Zhao et al., “Improving the Robustness of Large Language Models via Consistency Alignment,” arXiv preprint, pp. 1-11, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[29] Mathias Humbert et al., “Addressing the Concerns of the Lacks Family: Quantification of Kin Genomic Privacy,” Proceedings of the 2013 ACM SIGSAC Conference on Computer and Communication Security, pp. 1141-1152, 2013.
[CrossRef] [Google Scholar] [Publisher Link]

[30] Mathias Humbert et al., “Quantifying Interdependent Risks in Genomic Privacy,” ACM Transactions on Privacy and Security, vol. 20, no. 1, pp. 1-31, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[31] Reza Shokri et al., “Quantifying Location Privacy,” 2011 IEEE Symposium on Security & Privacy, 2011.
[CrossRef] [Google Scholar] [Publisher Link]

[32] Badhan Chandra Das, M. Hadi Amini, and Yanzhao Wu, “Privacy Risks Analysis and Mitigation in Federated Learning for Medical Images,” 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM’23), 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[33] Wenqi Wei et al., “A Framework for Evaluating Client Privacy Leakages in Federated Learning,” Computer Security—ESORICS 2020, pp. 545-566, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[34] Jonas Geiping et al., “Inverting Gradients—How Easy is it to Break Privacy in Federated Learning?,” Advances in Neural Information Processing Systems, 2020.
[Google Scholar] [Publisher Link]

[35] Oliver Cartwright, Harriet Dunbar, and Theo Radcliffe, “Evaluating Privacy Compliance in Commercial Large Language Models-ChatGPT, Claude, and Gemini,” Research Square, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[36] Vaidehi Patil, Peter Hase, and Mohit Bansal, “Can Sensitive Information be Deleted from LLMs? Objectives for Defending Against Extraction Attacks,” arXiv: 2309.1740, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[37] Jie Huang et al., “Are Large Pre-trained Language Models Leaking Your Personal Information?,” Findings of the Association for Computational Linguistics, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[38] Mohammad Raeini, “Privacy-preserving Large Language Models (PPLLMs),” SSRN, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[39] Ruihan Wu et al., “Learning to Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learning,” Proceedings of the 39^th Conference on Uncertainty in Artificial Intelligence, 2023.
[Google Scholar] [Publisher Link]

[40] Minxin Du et al., “Sun DP-Forward: Fine-tuning and Inference on Language models with Differential Privacy in Forward Pass,” Proceedings of the 2023 ACM SIGASAC Conference on Computer and Communications Security, pp. 2665-2679, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[41] Dingfan Chen, Ning Yu, and Mario Fritz, “RelaxLoss: Defending Membership Inference Attacks without Losing Utility,” arXiv: 2207.05801, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[42] Paul-Edouard Sarlin et al., “Superglue: Learning Feature Matching with Graph Neural Networks,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4938–4947, 2020.
[Google Scholar] [Publisher Link]

[43] Pranav Rajpurkar et al., “Squad: 100,000+ Questions for Machine Comprehension of Text,” Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 2383-2392, 2016.
[Google Scholar] [Publisher Link]

[44] Mandar Joshi et al., “Triviaqa: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension,” Proceedings of the 55^th Annual Meeting of the Association for Computational Linguistics, pp. 1601-1611, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[45] Siva Reddy, Danqi Chen, and Christopher D Manning, “Coqa: A Conversational Question Answering Challenge,” Transactions of the Association for Computational Linguistics, vol. 7, pp. 249–266, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[46] Tom Kwiatkowski et al., “Natural Questions: A Benchmark for Question Answering Research,” Transactions of the Association for Computational Linguistics, vol. 7, pp. 453–466, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[47] Deepak Narayanan et al., “Cheaply Evaluating Inference Efficiency Metrics for Autoregressive Transformer APIs,” arXiv: 2306.02440, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[48] Simran Arora et al., “Simple Linear Attention Language Models Balance the Recall-throughput Tradeoff,” arXiv: 2402.18668, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[49] Xiaoqi Jiao et al., “Tinybert: Distilling BERT for Natural Language Understanding,” Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 4163–4174, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[50] Chen Liang et al., “Less is More: Task-aware Layer-wise Distillation for Language Model Compression,” Proceedings of the 40^th International Conference on Machine Learning, 2023.
[Google Scholar] [Publisher Link]

[51] Atreya Shankar et al., “PrivacyGLUE: A Benchmark Dataset for General Language Understanding in Privacy Policies,” Applied Sciences, vol. 13, no. 6, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[52] Alex Havrilla, and Maia Iyer, “Understanding the Effect of Noise in LLM Training Data with Algorithmic Chains of Thought,” arXiv: 2402.04004, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[53] Jovan Stojkovic et al., “Dynamollm: Designing LLM Inference Clusters for Performance and Energy Efficiency,” 2025 IEEE International Symposium on High Performance Computer Architecture, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[54] Pratyush Patel et al., “Characterizing Power Management Opportunities for LLMs in the Cloud,” Proceedings of the 29^th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, vol. 3, pp. 207-222, 2024.
[CrossRef] [Google Scholar] [Publisher Link]