# Making Translators Privacy-aware on the User's Side

arXiv: https://arxiv.org/abs/2312.04068 · HTML: https://mlsanity.com/paper/2312.04068/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 51 references that are in the map.
- First posted on arXiv 7 Dec 2023.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [Differentially Private Learning with Adaptive Clipping](https://mlsanity.com/paper/1905.03871/) (2019)
- [A Survey on Homomorphic Encryption Schemes: Theory and Implementation](https://mlsanity.com/paper/1704.03578/) (2017)
- [Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations](https://mlsanity.com/paper/1910.08902/) (2019)
- [The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations](https://mlsanity.com/paper/1511.02301/) (2015)
- [Leveraging Hierarchical Representations for Preserving Privacy and Utility in Text](https://mlsanity.com/paper/1910.08917/) (2019)
- [A4NT: Author Attribute Anonymity by Adversarial Training of Neural Machine Translation](https://mlsanity.com/paper/1711.01921/) (2017)
- [ER-AE: Differentially Private Text Generation for Authorship Anonymization](https://mlsanity.com/paper/1907.08736/) (2019)
- [Embarrassingly Simple Text Watermarks](https://mlsanity.com/paper/2310.08920/) (2023)
- [Private Recommender Systems: How Can Users Build Their Own Fair Recommender Systems without Log Data?](https://mlsanity.com/paper/2105.12353/) (2021)
- [Towards Principled User-side Recommender Systems](https://mlsanity.com/paper/2208.09864/) (2022)
- [Retrieving Black-box Optimal Images from External Databases](https://mlsanity.com/paper/2112.14921/) (2021)
- [CLEAR: A Fully User-side Image Search System](https://mlsanity.com/paper/2206.08521/) (2022)

## Built on by (most cited first, 3 of 3)

- [Overhead-free User-side Recommender Systems](https://mlsanity.com/paper/2411.07589/) (2024)
- [Solving the Cold Start Problem on One's Own as an End User via Preference Transfer](https://mlsanity.com/paper/2502.12398/) (2025)
- [AgentRecommender: LLM Agents Enable Customizable Recommender Systems on the User Side](https://mlsanity.com/paper/2609.31166/) (2026)

## Abstract (arXiv)

We propose PRISM to enable users of machine translation systems to preserve the privacy of data on their own initiative. There is a growing demand to apply machine translation systems to data that require privacy protection. While several machine translation engines claim to prioritize privacy, the extent and specifics of such protection are largely ambiguous. First, there is often a lack of clarity on how and to what degree the data is protected. Even if service providers believe they have sufficient safeguards in place, sophisticated adversaries might still extract sensitive information. Second, vulnerabilities may exist outside of these protective measures, such as within communication channels, potentially leading to data leakage. As a result, users are hesitant to utilize machine translation engines for data demanding high levels of privacy protection, thereby missing out on their benefits. PRISM resolves this problem. Instead of relying on the translation service to keep data safe, PRISM provides the means to protect data on the user's side. This approach ensures that even machine translation engines with inadequate privacy measures can be used securely. For platforms already equipped with privacy safeguards, PRISM acts as an additional protection layer, reinforcing their security furthermore. PRISM adds these privacy features without significantly compromising translation accuracy. Our experiments demonstrate the effectiveness of PRISM using real-world translators, T5 and ChatGPT (GPT-3.5-turbo), and the datasets with two languages. PRISM effectively balances privacy protection with translation accuracy.