EW-Tune: A Framework for Privately Fine-Tuning Large Language Models with Differential Privacy
Open accessAbstract
Pre-trained Large Language Models (LLMs) are an integral part of modern AI that have led to breakthrough performances in complex AI tasks. Major AI companies with expensive infrastructures are able to develop and train these large models with billions and millions of parameters from scratch. Third parties, researchers, and practitioners are increasingly adopting these pre-trained models and fine-tuning them on their private data to accomplish their downstream AI tasks. However, it has been shown that an adversary can extract/reconstruct the exact training samples from these LLMs, which can lead to revealing personally identifiable information. The issue has raised deep concerns about the privacy of LLMs. Differential privacy (DP) provides a rigorous framework that allows adding noise in the process of training or fine-tuning LLMs such that extracting the training data becomes infeasible (i.e., with a cryptographically small success probability). While the theoretical privacy guarantees offered in most extant studies assume learning models from scratch through many training iterations in an asymptotic setting, this assumption does not hold in fine-tuning scenarios in which the number of training iterations is significantly smaller. To address the gap, we present EW-Tune, a DP framework for fine-tuning LLMs based on Edgeworth accountant with finite-sample privacy guarantees. Our results across four well-established natural language understanding (NLU) tasks show that while EW-Tune adds privacy guarantees to LLM fine-tuning process, it directly contributes to decreasing the induced noise to up to 5.6% and improves the state-of-the-art LLMs performance by up to 1.1% across all NLU tasks. We have open-sourced our implementations for wide adoption and public testing purposes.
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
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?
MoE models face challenges in fine-tuning and require substantial memory for inference due to necessity of loading all experts into VRAM.
“However, they face challenges in fine-tuning and require substantial memory for inference due to the necessity of loading all experts into Video Random Access Memory (VRAM) [289], [290], [110].”
From From Google Gemini to OpenAI Q* (Q-Star): A Survey on Reshaping the Generative Artificial Intelligence (AI) Research Landscape (2025) · cites this paper as [290]
MoE models, notably Mixtral 8x7B, have superior pretraining speed compared to dense models.
“MoE models, notably Mixtral 8x7B, are renowned for their superior pretraining speed compared to dense models”
From From Google Gemini to OpenAI Q* (Q-Star): A Survey on Reshaping the Generative Artificial Intelligence (AI) Research Landscape (2025) · cites this paper as [290]
MoE models face hurdles in fine-tuning and demand considerable VRAM for inference because all experts must be loaded.
“yet they face hurdles in fine-tuning and demand considerable VRAM for inference, owing to the requirement of loading all experts [289], [290], [110].”
From From Google Gemini to OpenAI Q* (Q-Star): A Survey on Reshaping the Generative Artificial Intelligence (AI) Research Landscape (2025) · cites this paper as [290]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 48,293 · see citing works
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · see citing works
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515 · see citing works
Kaugeranna, R., Kaugeranna, E., & Aion, (. S. 4. 6. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.giscience.2023.43 · Cited by 13,695 · see citing works
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929 · see citing works
Calibrating Noise to Sensitivity in Private Data Analysis
Dwork, C., McSherry, F., Nissim, K., & Smith, A. (2006) · Lecture Notes in Computer Science · doi:10.1007/11681878_14 · Cited by 7,272 · see citing works
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C. D., Ng, A., & Potts, C. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1170 · Cited by 6,878 · see citing works
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1906.08237 · Cited by 6,687 · see citing works
Deep Learning with Differential Privacy
Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978318 · Cited by 6,578 · see citing works
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. (2018) · Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w18-5446 · Cited by 4,222 · see citing works
A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference
Williams, A., Nangia, N., & Bowman, S. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1101 · Cited by 3,342 · see citing works
Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
Fredrikson, M., Jha, S., & Ristenpart, T. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813677 · Cited by 2,961 · see citing works
Zero-shot text-to-image generation
Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., Chen, M., & Sutskever, I. (2021) · arXiv · doi:10.48550/arxiv.2102.12092 · Cited by 2,417 · see citing works
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
Baevski, A., Zhou, H., Mohamed, A., & Auli, M. (2020) · arXiv · doi:10.48550/arxiv.2006.11477 · Cited by 2,369 · see citing works
Mironov, I. (2017) · 2017 IEEE 30th Computer Security Foundations Symposium (CSF) · doi:10.1109/csf.2017.11 · Cited by 1,255 · see citing works
Extracting Training Data from Large Language Models
Carlini, N., Tramer, F., Wallace, E., Jagielski, M., Herbert-Voss, A., Lee, K., Roberts, A., Brown, T., Song, D., Erlingsson, U., et al. (2020) · arXiv · doi:10.48550/arxiv.2012.07805 · Cited by 727 · see citing works
The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks
Carlini, N., Liu, C., Erlingsson, Ú., Kos, J., & Song, D. (2018) · arXiv · doi:10.48550/arxiv.1802.08232 · Cited by 629 · see citing works
Dong, J., Roth, A., & Su, W. (2022) · Journal of the Royal Statistical Society Series B (Statistical Methodology) · doi:10.1111/rssb.12454 · Cited by 428 · see citing works
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing
Yarowsky, D., Baldwin, T., Korhonen, A., Livescu, K., & Bethard, S. J. (2013) · Empirical Methods in Natural Language Processing · Cited by 422 · see citing works
The composition theorem for differential privacy
Kairouz, P., Oh, S., & Viswanath, P. (2017) · IEEE Transactions on Information Theory · doi:10.1109/tit.2017.2685505 · Cited by 408 · see citing works
Dong, J., Roth, A., & Su, W. J. (2019) · arXiv · doi:10.48550/arxiv.1905.02383 · Cited by 389 · see citing works
Concentrated Differential PrivacyPreprint
Dwork, C., & Rothblum, G. N. (2016) · arXiv (Cornell University) · doi:10.4230/lipics.forc.2026.4 · Cited by 372 · see citing works
Deep Learning With Gaussian Differential Privacy
Bu, Z., Dong, J., Long, Q., & Wei-Jie, S. (2020) · Harvard Data Science Review · doi:10.1162/99608f92.cfc5dd25 · Cited by 172 · see citing works
End-to-End Neural Pipeline for Goal-Oriented Dialogue Systems using GPT-2
Ham, D., Lee, J.-G., Jang, Y., & Kim, K.-E. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.54 · Cited by 161 · see citing works
Differentially Private Fine-tuning of Language Models
Yu, D., Naik, S., Bačkurs, A., Gopi, S., Inan, H. A., Kamath, G., Kulkarni, J., Lee, Y. T., Manoel, A., Wutschitz, L., et al. (2024) · Journal of Privacy and Confidentiality · doi:10.29012/jpc.880 · Cited by 152 · see citing works
Differentially Private Fine-tuning of Language Models
Yu, D., Naik, S., Backurs, A., Gopi, S., Inan, H. A., Kamath, G., Kulkarni, J., Lee, Y. T., Manoel, A., Wutschitz, L., et al. (2021) · arXiv · doi:10.48550/arxiv.2110.06500 · Cited by 101 · see citing works
Hisamoto, S., Post, M., & Duh, K. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00299 · Cited by 86 · see citing works
Transformer-based Conditional Variational Autoencoder for Controllable Story GenerationPreprint
Fang, L., Zeng, T., Liu, C., Bo, L., Dong, W., & Chen, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.00828 · Cited by 53 · see citing works
Large Scale Private Learning via Low-rank ReparametrizationPreprint
Yu, D., Zhang, H., Chen, W., Yin, J., & Liu, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.09352 · Cited by 40 · see citing works
Computing Tight Differential Privacy Guarantees Using FFT
Koskela, A., Jälkö, J., & Honkela, A. (2019) · Työväentutkimus Vuosikirja · Cited by 29 · see citing works
Meiser, S., & Mohammadi, E. (2018) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3243734.3243765 · Cited by 27 · see citing works
Deep Learning with Gaussian Differential PrivacyPreprint
Bu, Z., Dong, J., Long, Q., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.11607 · Cited by 20 · see citing works
Hu, J. L., Ebrahimi, M. R., & Chen, H. (2021) · IEEE International Conference on Intelligence and Security Informatics (ISI) · doi:10.1109/isi53945.2021.9624787 · Cited by 17 · see citing works
Self-citationEdgeworth Accountant: An Analytical Approach to Differential Privacy Composition
Wang, H., Gao, S., Zhang, H., Shen, M., Su, W., & Wu, J. (2026) · Journal of the American Statistical Association · doi:10.1080/01621459.2026.2668139 · Cited by 6 · see citing works
Halevi, S., & Rabin, T. (2006) · Digital Access to Libraries (Université catholique de Louvain (UCL), l'Université de Namur (UNamur) and the Université Saint-Louis (USL-B)) · doi:10.1007/11681878 · Cited by 1 · see citing works
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805
Flagged first, then by citations
Research works printed but not linked: 3
- [5][5] A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, I. Sutskever et al. , 'Language models are unsupervised multitask learners,' OpenAI blog , vol. 1, no. 8, p. 9, 2019. -
- [14][14] H. Wang, S. Gao, H. Zhang, M. Shen, and W. J. Su, 'Analytical composition of differential privacy via the edgeworth accountant,' arXiv preprint arXiv:2206.04236 , 2022. - · arXiv
- [25][25] S. Gopi, Y. T. Lee, and L. Wutschitz, 'Numerical composition of differential privacy,' in Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual , M. Ranzato, A. Beygelzimer, Y. N. Dauphin, P. Liang, and J. W. Vaughan, Eds., 2021, pp. 11 631-11 642. [Online]. Available: https://proceedings.neurips.cc/ paper/2021/hash/6097d8f3714205740f30debe1166744e-Abstract.html -
Cited by
Sorted by citations
Privacy-Preserving Techniques in Generative AI and Large Language Models: A Narrative Review
Feretzakis, G., Papaspyridis, K., Gkoulalas-Divanis, A., & Verykios, V. S. (2024) · Information · doi:10.3390/info15110697 · Cited by 176 · see citing works
Large Language Models for UAVs: Current State and Pathways to the Future
Javaid, S., Fahim, H., He, B., & Saeed, N. (2024) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2024.3446799 · Cited by 148 · see citing works
On Protecting the Data Privacy of Large Language Models (LLMs): A Survey
Yan, B., Li, K., Xu, M., Dong, Y., Zhang, Y., Ren, Z., & Cheng, X. (2024) · International Conference on Meta Computing (ICMC) · doi:10.1109/icmc60390.2024.00008 · Cited by 187 · see citing works
Leveraging error-assisted fine-tuning large language models for manufacturing excellence
Xia, L., Li, C., Zhang, C., Liu, S., & Zheng, P. (2024) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2024.102728 · Cited by 105 · see citing works
McIntosh, T. R., Susnjak, T., Liu, T., Watters, P., Xu, D., Liu, D., & Halgamuge, M. N. (2025) · Technologies · doi:10.3390/technologies13020051 · Cited by 102 · see citing works
“• Fine Tuning: Involves customizing pre-trained models to specific domains or user preferences, enhancing accuracy and relevance for niche applications [60], [258], [259].”
BackgroundOn protecting the data privacy of Large Language Models (LLMs) and LLM agents: A literature review
Yan, B., Li, K., Xu, M., Dong, Y., Zhang, Y., Ren, Z., & Cheng, X. (2025) · High-Confidence Computing · doi:10.1016/j.hcc.2025.100300 · Cited by 93 · see citing works
Whispered Tuning: Data Privacy Preservation in Fine-Tuning LLMs through Differential Privacy
Singh, T., Aditya, H., Madisetti, V. K., & Bahga, A. (2024) · Journal of Software Engineering and Applications · doi:10.4236/jsea.2024.171001 · Cited by 29 · see citing works
Budakoglu, G., & Emekci, H. (2025) · IEEE Access · doi:10.1109/access.2025.3542334 · Cited by 26 · see citing works
Selective privacy-preserving framework for large language models fine-tuning
Wang, T., Zhai, L., Yang, T., Luo, Z., & Liu, S. (2024) · Information Sciences · doi:10.1016/j.ins.2024.121000 · Cited by 23 · see citing works
LLM-Powered AI Agent Systems and Their Applications in Industry
Liang, G., & Tong, Q. (2025) · IEEE World AI IoT Congress (AIIoT) · doi:10.1109/aiiot65859.2025.11105299 · Cited by 32 · see citing works
Privacy in Fine-Tuning Large Language Models: Attacks, Defenses, and Future Directions
Du, H., Liu, S., Zheng, L., Cao, Y., Nakamura, A., & Chen, L. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-8183-9_25 · Cited by 23 · see citing works
A Survey on Security and Privacy of Multimodal LLMs - Connected Healthcare Perspective
Rahman, M. A. (2023) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps58843.2023.10465035 · Cited by 18 · see citing works
A Survey of Reasoning with Foundation ModelsPreprint
Sun, J., Zheng, C., Xie, E., Liu, Z., Chu, R., Liu, J., Xu, J., Ding, M., Li, H., Geng, M., et al. (2023) · doi:10.31219/osf.io/ac4sp · Cited by 137 · see citing works
SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation
Shanmugarasa, Y., Ding, M., Chamikara, M. A. P., & Rakotoarivelo, T. (2025) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/3708821.3733888 · Cited by 31 · see citing works
Grounding Foundation Models through Federated Transfer Learning: A General Framework
Kang, Y., Fan, T., Gu, H., Zhang, X., Fan, L., & Yang, Q. (2025) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3742788 · Cited by 21 · see citing works
Generative AI and digital resilience: a research agenda
Große, C., & Sundberg, L. (2025) · Journal of Risk Research · doi:10.1080/13669877.2025.2539105 · Cited by 15 · see citing works
SpeechCraft: An Integrated Data Generation Pipeline from Videos for LLM Finetuning
Jyothi Swaroop Arlagadda, N., Vuppalapati, V. S. M., Modi, S., Vishwakarma, R., & Shah, H. (2024) · International Conference on Automation and Computing (ICAC) · doi:10.1109/icac61394.2024.10718747 · Cited by 11 · see citing works
Fine-Tuning Large Language Models for Task Specific Data
Ramesh, R., Akarsh Thejasvi Raju, M., Reddy, H. V., & Sandeep Varma, N. (2024) · International Conference on Networking, Embedded and Wireless Systems (ICNEWS) · doi:10.1109/icnews60873.2024.10730913 · Cited by 10 · see citing works
Evolutionary game analysis of stakeholder privacy management in the AIGC model
Lv, Y., Yang, J. H., Sun, X., & Wu, H. (2025) · Operations Research Perspectives · doi:10.1016/j.orp.2025.100327 · Cited by 10 · see citing works
Privacy-Aware Detection for Large Language Models Using a Hybrid BiLSTM-HMM Approach
Abbasalizadeh, M., & Narain, S. (2025) · IEEE Access · doi:10.1109/access.2025.3587988 · Cited by 10 · see citing works
Sigalov, S. E., Cohen, A., & Nachmias, R. (2024) · Journal of Computers in Education · doi:10.1007/s40692-024-00334-x · Cited by 14 · see citing works
Luo, J., Zhang, Y., Zhang, Z., Liu, S., Dong, Y., Li, H., Yu, Y. S., Wang, H., Zhou, X., & Xu, Z. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11466-6 · Cited by 7 · see citing works
Huang, D., Ge, M., Xiang, K., Zhang, X.-L., & Yang, H. (2024) · International Journal of Network Management · doi:10.1002/nem.2292 · Cited by 6 · see citing works
Reliability and security: from swarm robots to AI agents
Yan, Y., Xie, Y., Tang, J., Li, Y., & Jin, Y. (2025) · Journal of Reliability Science and Engineering · doi:10.1088/3050-2454/adea7a · Cited by 5 · see citing works
Privacy dilemmas and opportunities in large language models: a brief review
Li, H., Ye, J., & Wu, J. (2025) · Frontiers of Computer Science · doi:10.1007/s11704-024-40583-8 · Cited by 6 · see citing works
Ahmadi, K., Behnia, R., Ebrahimi, R., Kermani, M. M., Birrell, J., Pacheco, J. L., & Yavuz, A. A. (2025) · IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw67851.2025.00035 · Cited by 4 · see citing works
Self-citationPrivacy Aware Question-Answering System for Online Mental Health Risk Assessment
Chhikara, P., Pasupulety, U., Marshall, J., Chaurasia, D., & Kumari, S. (2023) · Workshop on Biomedical Language Processing (BioNLP) · doi:10.18653/v1/2023.bionlp-1.18 · Cited by 4 · see citing works
Email subjects generation with large language models: GPT-3.5, PaLM 2, and BERT
Loukili, S., Fennan, A., & Elaachak, L. (2024) · International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering · doi:10.11591/ijece.v14i4.pp4655-4663 · Cited by 5 · see citing works
Differential Privacy Mechanisms in Neural Tangent Kernel Regression
Gu, J., Liang, Y., Sha, Z., Shi, Z., & Song, Z. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00234 · Cited by 5 · see citing works
Exploring user privacy awareness on GitHub: an empirical study
Alfieri, C., Rocco, J. D., Inverardi, P., & Nguyen, P. T. (2024) · Empirical Software Engineering · doi:10.1007/s10664-024-10544-7 · Cited by 4 · see citing works
(2024) · International Research Journal of Modernization in Engineering Technology and Science · doi:10.56726/irjmets50070 · Cited by 3 · see citing works
Coffey, S., Catudal, J. W., & Bastian, N. D. (2024) · Assurance and Security for AI-enabled Systems · doi:10.1117/12.3013129 · Cited by 2 · see citing works
Ji, L., Xiao, S., Xu, B. L., & Zhang, H. (2024) · IEEE International Conference on Software Quality, Reliability and Security (QRS) · doi:10.1109/qrs62785.2024.00054 · Cited by 2 · see citing works
Differentially Private Fine-Tuning of Large Language Models: A Survey
Yu, M., & Singh, P. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3462-3_8 · Cited by 2 · see citing works
Data protection in the era of large language models: challenges and opportunities
Revesai, Z., & Chipfumbu, C. T. (2026) · AI and Ethics · doi:10.1007/s43681-026-01223-y · Cited by 5 · see citing works
Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4
Mandal, B., Amariucai, G. T., & Wei, S. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10651289 · Cited by 2 · see citing works
Effectiveness of Privacy-Preserving Algorithms for Large Language Models: A Benchmark Analysis
Sun, J., Suleiman, B., & Ullah, I. (2024) · Conference on Privacy, Security and Trust · doi:10.1109/pst62714.2024.10788045 · Cited by 2 · see citing works
Kirti, C., Chattopadhyay, A., Anand, A., & Guha, P. (2023) · International Conference on Asian Language Processing · doi:10.1109/ialp61005.2023.10337315 · Cited by 2 · see citing works
Passarella, L. S., Begoli, E., Smith, C. J., & Sadovnik, A. (2025) · SN Computer Science · doi:10.1007/s42979-025-03807-7 · Cited by 1 · see citing works
Guardians of Privacy: Leveraging LLMs in Assistive Robotic Systems for Healthcare
Zoughalian, K., Aitsam, M., Marchang, J., & Nuovo, A. G. D. (2025) · IEEE Conference on Communications and Network Security · doi:10.1109/cns66487.2025.11195035 · Cited by 1 · see citing works
Liu, S., Yan, J., Wang, X., Jiang, Y., Chen, L., Fan, T., Chen, K., & Yang, Q. (2025) · ACM International Conference on AI in Finance (ICAIF) · doi:10.1145/3768292.3770339 · Cited by 1 · see citing works
Chlasta, K. (2026) · Security and Defence Quarterly · doi:10.35467/sdq/217364 · Cited by 3 · see citing works
Contextual Integrity in Large Language Models: A Review
Hassanpour, A., & Yang, B. (2026) · Journal of Cybersecurity and Privacy · doi:10.3390/jcp6020074 · Cited by 1 · see citing works
Trustworthiness Evaluation of Large Language Models
Chen, P., & Liu, S. (2025) · Springer eBooks · doi:10.1007/978-3-031-76770-8_12 · Cited by 2 · see citing works
Private Matrix Factorization with Public Item Features
Curmei, M., Krichene, W., Zhang, L. L., & Sundararajan, M. (2023) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/3604915.3608833
Towards Responsible AI: Understanding and Mitigating Ethical Concerns of Large Language Models
Upadhye, A. (2024) · Journal of Artificial Intelligence & Cloud Computing · doi:10.47363/jaicc/2024(3)289
Towards Reducing Latency Using Beam Search in an Interactive Conversational Speech Agent
Ott, N., Horst, R., & Dörner, R. (2024) · IEEE Gaming, Entertainment, and Media Conference (GEM) · doi:10.1109/gem61861.2024.10585772
Exploring Neural and Prompt-Based Approaches for Event Detection in Short Stories
Kirti, C., Anand, A., & Guha, P. (2024) · International Journal of Asian Language Processing · doi:10.1142/s2717554524500085
Mobile AI-Generated Content Data Sharing Privacy-Preserving Scheme for Logistics IoT in 6G Era
Li, K., Wang, R.-Y., Wang, H., & Wang, Y. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-4509-1_14
Navigating Trustworthiness in LLMs: An Examination of Privacy, Security, and Robustness
Dang, K., & Lai, P. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-6389-7_1
Generating Secure Artificial Intelligence Model Source Code: A Reinforcement Learning Approach
Kathikar, A., Lazarine, B., Gao, Y., Shah, A., & Samtani, S. (2025) · IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw67851.2025.00037
A Survey of Privacy Preservation Techniques for Large Language Models
Zhang, Y., Chen, X., Cai, W., & Zhang, H. (2025) · IEEE International Conference on Cyber Security and Cloud Computing / IEEE International Conference on Edge Computing and Scalable Cloud (CSCloud/EdgeCom) · doi:10.1109/edgecom66327.2025.00036
Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating
Cao, X., Zhang, J., Kan, M., Shan, S., & Chen, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37211-6_12
ADP-LoRA: Privacy-Preserving Low-Rank Fine-Tuning of Transformers with Adaptive Differential Privacy
Mahesh, R., & Veeramani, K. (2025) · International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT) · doi:10.1109/iconscept66142.2025.11437153
Mbounkap, J., Djigo, H., Masheh, T., Nzooh, A., & Kar, A. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7685-1.ch013 · Cited by 1 · see citing works
Is There a Structural Privacy Risk in Graph Prompting with LLMs?
Zhu, J., Lin, X. L., Qi, Y., Mao, Q., Li, J., & Wu, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-0375-8_32
PC-FT: A Lightweight and Utility-Preserving Private Fine-Tuning Framework for Edge-Based Agentic AI
Zhang, P., Zhang, R., Lv, Z., Fan, Q., Yuan, S., & Guan, Z. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3694751
Mitigating Security Risks in Large Language Models: A Full Lifecycle Perspective
Wang, Y. K., Bai, Z., Huo, J., Wang, B., Liu, J., Cao, H., Meng, F., Yang, X., & Gao, Y. (2026) · Machine Learning · doi:10.1007/s10994-025-06930-x
Refahi, M. S., Yoo, H., Hearne, G., Allegra, C., Brown, J. R., Sokhansanj, B. A., Woloszynek, S., Ramjattun, K., Allipilli, S. R., Robi Polikar, A., et al. (2026) · Springer eBooks · doi:10.1007/978-3-032-18509-9_3
Baali, F. A., Lhasnaoui, C., Ait‐Mlouk, A., & Agouti, T. (2026) · Machine Learning · doi:10.1007/s10994-026-07142-7
- Authors
- Behnia, R., Ebrahimi, M. R., Pacheco, J., & Padmanabhan, B.
- Affiliations
- University of South Florida (US)
- University of Arizona (US)
- Venue
- 2022 IEEE International Conference on Data Mining Workshops (ICDMW)
- Publisher
- IEEE
- Published
- 2022-11
- Pages
- 560-566
- ISSN
- 2375-9259 (ISSN-L)
- OpenAlex
- W4319780902
- Cited by
- 60
- References
- 34
- Citations by year
- 2026: 10 · 2025: 25 · 2024: 20 · 2023: 5
- FWCI
- 6.91
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE ... International Conference on Data Mining workshops (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- University of Pennsylvania
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Social Sciences › Sociology and Political Science › Privacy, Security, and Data Protection
- Keywords
- large language models, differential privacy, fine-tuning, training data extraction, privacy-preserving machine learning, natural language understanding
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
