# Privacy-Preserving Language Model Inference with Instance Obfuscation

arXiv: https://arxiv.org/abs/2402.08227 · HTML: https://mlsanity.com/paper/2402.08227/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 32 references that are in the map.
- First posted on arXiv 13 Feb 2024.

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Black-Box Tuning for Language-Model-as-a-Service](https://mlsanity.com/paper/2201.03514/) (2022)
- [Information Leakage in Embedding Models](https://mlsanity.com/paper/2004.00053/) (2020)
- [Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity](https://mlsanity.com/paper/2102.03065/) (2021)
- [Augmenting Data with Mixup for Sentence Classification: An Empirical Study](https://mlsanity.com/paper/1905.08941/) (2019)
- [Offsite-Tuning: Transfer Learning without Full Model](https://mlsanity.com/paper/2302.04870/) (2023)
- [Differential Privacy for Text Analytics via Natural Text Sanitization](https://mlsanity.com/paper/2106.01221/) (2021)
- [Towards Robust and Privacy-preserving Text Representations](https://mlsanity.com/paper/1805.06093/) (2018)
- [THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption](https://mlsanity.com/paper/2206.00216/) (2022)
- [Label-Only Model Inversion Attacks via Boundary Repulsion](https://mlsanity.com/paper/2203.01925/) (2022)
- [Natural Language Understanding with Privacy-Preserving BERT](https://mlsanity.com/paper/2104.07504/) (2021)
- [Privacy-preserving Neural Representations of Text](https://mlsanity.com/paper/1808.09408/) (2018)
- [A Differentially Private Text Perturbation Method Using a Regularized Mahalanobis Metric](https://mlsanity.com/paper/2010.11947/) (2020)
- [CAPE: Context-Aware Private Embeddings for Private Language Learning](https://mlsanity.com/paper/2108.12318/) (2021)
- [CryptoGRU: Low Latency Privacy-Preserving Text Analysis With GRU](https://mlsanity.com/paper/2010.11796/) (2020)
- [Security and Privacy Issues in Cloud Computing](https://mlsanity.com/paper/1303.4814/) (2013)

## Built on by (most cited first, 7 of 7)

- [Privacy Preserving Prompt Engineering: A Survey](https://mlsanity.com/paper/2404.06001/) (2024)
- [A Survey on Privacy Risks and Protection in Large Language Models](https://mlsanity.com/paper/2505.01976/) (2025)
- [LLM Access Shield: Domain-Specific LLM Framework for Privacy Policy Compliance](https://mlsanity.com/paper/2505.17145/) (2025)
- [Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks](https://mlsanity.com/paper/2504.17421/) (2025)
- [SoK: Privacy-aware LLM in Healthcare: Threat Model, Privacy Techniques, Challenges and Recommendations](https://mlsanity.com/paper/2601.10004/) (2026)
- [Confidential Prompting: Privacy-preserving LLM Inference on Cloud](https://mlsanity.com/paper/2409.19134/) (2024)
- [Beyond Local vs. External: A Game-Theoretic Framework for Trustworthy Knowledge Acquisition](https://mlsanity.com/paper/2604.23413/) (2026)

## Abstract (arXiv)

Language Models as a Service (LMaaS) offers convenient access for developers and researchers to perform inference using pre-trained language models. Nonetheless, the input data and the inference results containing private information are exposed as plaintext during the service call, leading to privacy issues. Recent studies have started tackling the privacy issue by transforming input data into privacy-preserving representation from the user-end with the techniques such as noise addition and content perturbation, while the exploration of inference result protection, namely decision privacy, is still a blank page. In order to maintain the black-box manner of LMaaS, conducting data privacy protection, especially for the decision, is a challenging task because the process has to be seamless to the models and accompanied by limited communication and computation overhead. We thus propose Instance-Obfuscated Inference (IOI) method, which focuses on addressing the decision privacy issue of natural language understanding tasks in their complete life-cycle. Besides, we conduct comprehensive experiments to evaluate the performance as well as the privacy-protection strength of the proposed method on various benchmarking tasks.