Privacy and Security Challenges in Large Language Models
The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Large Language Models (LLMs) are at the forefront of artificial intelligence advancements, demonstrating exceptional capabilities in natural language understanding and generation across diverse domains such as healthcare, finance, and customer service. However, their deployment introduces substantial secu-rity and privacy risks, including prompt injection, data leakage, and unauthorized data disclosures. These vulnerabilities highlight the need for robust frameworks to safeguard sensitive data and prevent misuse. This paper provides a comprehensive analysis of the security and privacy challenges in LLMs, examines existing mitigation strategies such as intelligent LLM firewalls, differen-tial privacy, and OW ASP-based security principles, and discusses future directions for ethical and secure LLM deployment. By addressing these challenges in detail, we identify gaps in current practices and propose a roadmap for the secure and responsible deployment of LLMs in high-stakes applications. Our findings underscore the importance of tailored security frameworks and privacy-preserving techniques to ensure the ethical and reliable use of LLMs in sensitive environments. Additionally, this pa-per emphasizes the significance of a human-in-the-loop (HITL) approach to ensure accountability and accuracy, particularly in critical domains. The discussion extends to emerging technologies such as retrieval-augmented generation (RAG) and adaptive threat detection systems, which hold promise for enhancing the security and ethical deployment of LLMs.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Emergent Abilities of Large Language Models
Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., Metzler, D., et al. (2022) · arXiv · doi:10.48550/arxiv.2206.07682 · Cited by 1,264 · cited 3×
“Furthermore, since LLMs are used in decision-critical scenarios, such as autonomous systems and predictive analytics, their reliability and interpretability become increasingly vital to promote trust between stakeholders [5].”
A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly
Yao, Y., Duan, J., Xu, K., Cai, Y., Sun, Z., & Zhang, Y. (2024) · High-Confidence Computing · doi:10.1016/j.hcc.2024.100211 · Cited by 1,083 · cited 1×
“LLMs is trained on vast amounts of data which are susceptible to various threats, including adversarial attacks, data leakage, and prompt injection vulnerabilities [3].”
Security and Privacy Challenges of Large Language Models: A Survey
Das, B. C., Amini, M. H., & Wu, Y. (2025) · ACM Computing Surveys · doi:10.1145/3712001 · Cited by 445 · cited 2×
“Input validation, strict prompt filtering, and employing intelligent LLM firewalls for real-time monitoring [9], [10], [23].”
Haltaufderheide, J., & Ranisch, R. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01157-x · Cited by 396
Enhancing Trust in LLMs: Algorithms for Comparing and Interpreting LLMs
Brown, N. B. (2024) · arXiv · doi:10.48550/arxiv.2406.01943 · Cited by 14
Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
Wen, J., Hebbar, V., Larson, C., Bhatt, A., Radhakrishnan, A., Sharma, M., Sleight, H., Feng, S., He, H., Perez, E., et al. (2024) · arXiv · doi:10.48550/arxiv.2411.17693 · Cited by 1 · cited 1×
“These frameworks could leverage advanced machine learning models for real-time threat detection and response, enabling systems to proactively identify and mitigate novel attack vectors [28]. essential for achieving these objectives.”
Cited by
Chow, J. C. L., & Li, K. (2025) · Information · doi:10.3390/info16070549 · Cited by 84
Brohi, S., Mastoi, Q.-U.-A., Jhanjhi, N. Z., & Pillai, T. R. (2025) · Algorithms · doi:10.3390/a18080499 · Cited by 69
“While the limitations of LLMs in handling secure or sensitive information are reasonably well studied [41,47,48,78], the risks become significantly more complex once these models are embedded into agents that can autonomously access external systems, trigger actions, and exchange data without…”
Jaffal, N. O., Alkhanafseh, M., & Mohaisen, D. (2025) · AI · doi:10.3390/ai6090216 · Cited by 69
Metadata
- Authors
- Rathod, V., Nabavirazavi, S., Zad, S., & Iyengar, S. S.
- Venue
- 2025 IEEE 15th Annual Computing and Communication Workshop and Conference (CCWC)
- Publisher
- IEEE
- Published
- 2025-01-06
- Pages
- 00746-00752
- OpenAlex
- W4411985537
- Cited by
- 36
- References
- 6
- FWCI
- 36.31
- Type
- conference paper
- Language
- en
- Open access
- closed
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Privacy and Security Challenges in Large Language Models. https://app.cochat.ai/papers/10.1109/ccwc62904.2025.10903912
- The paper
- Rathod, V., Nabavirazavi, S., Zad, S., & Iyengar, S. S. (2025). Privacy and Security Challenges in Large Language Models. 2025 IEEE 15th Annual Computing and Communication Workshop and Conference (CCWC). https://doi.org/10.1109/ccwc62904.2025.10903912
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.