# Evaluating Apple Intelligence's Writing Tools for Privacy Against Large Language Model-Based Inference Attacks: Insights from Early Datasets

arXiv: https://arxiv.org/abs/2506.03870 · HTML: https://mlsanity.com/paper/2506.03870/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 41 references that are in the map.
- First posted on arXiv 4 Jun 2025.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Pre-trained Models for Natural Language Processing: A Survey](https://mlsanity.com/paper/2003.08271/) (2020)
- [Sentiment Analysis in the Era of Large Language Models: A Reality Check](https://mlsanity.com/paper/2305.15005/) (2023)
- [Security and Privacy Challenges of Large Language Models: A Survey](https://mlsanity.com/paper/2402.00888/) (2024)
- [Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities](https://mlsanity.com/paper/2308.12833/) (2023)
- [Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification](https://mlsanity.com/paper/2406.08660/) (2024)
- [RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting](https://mlsanity.com/paper/2305.15685/) (2023)
- [EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis](https://mlsanity.com/paper/2401.08508/) (2024)
- [A Comparative Analysis of Word-Level Metric Differential Privacy: Benchmarking The Privacy-Utility Trade-off](https://mlsanity.com/paper/2404.03324/) (2024)
- [Unlocking the Potential of Large Language Models for Clinical Text Anonymization: A Comparative Study](https://mlsanity.com/paper/2406.00062/) (2024)
- [Do Emotions Really Affect Argument Convincingness? A Dynamic Approach with LLM-based Manipulation Checks](https://mlsanity.com/paper/2503.00024/) (2025)
- [A Federated Learning Approach to Privacy Preserving Offensive Language Identification](https://mlsanity.com/paper/2404.11470/) (2024)

## Abstract (arXiv)

The misuse of Large Language Models (LLMs) to infer emotions from text for malicious purposes, known as emotion inference attacks, poses a significant threat to user privacy. In this paper, we investigate the potential of Apple Intelligence's writing tools, integrated across iPhone, iPad, and MacBook, to mitigate these risks through text modifications such as rewriting and tone adjustment. By developing early novel datasets specifically for this purpose, we empirically assess how different text modifications influence LLM-based detection. This capability suggests strong potential for Apple Intelligence's writing tools as privacy-preserving mechanisms. Our findings lay the groundwork for future adaptive rewriting systems capable of dynamically neutralizing sensitive emotional content to enhance user privacy. To the best of our knowledge, this research provides the first empirical analysis of Apple Intelligence's text-modification tools within a privacy-preservation context with the broader goal of developing on-device, user-centric privacy-preserving mechanisms to protect against LLMs-based advanced inference attacks on deployed systems.