This paper examines the evolving landscape of machine learning (ML) and its
profound impact across various sectors, with a special focus on the emerging
field of Privacy-preserving Machine Learning (PPML). As ML applications become
increasingly integral to industries like telecommunications, financial
technology, and surveillance, they raise significant privacy concerns,
necessitating the development of PPML strategies. The paper highlights the
unique challenges in safeguarding privacy within ML frameworks, which stem from
the diverse capabilities of potential adversaries, including their ability to
infer sensitive information from model outputs or training data.
We delve into the spectrum of threat models that characterize adversarial
intentions, ranging from membership and attribute inference to data
reconstruction. The paper emphasizes the importance of maintaining the
confidentiality and integrity of training data, outlining current research
efforts that focus on refining training data to minimize privacy-sensitive
information and enhancing data processing techniques to uphold privacy.
Through a comprehensive analysis of privacy leakage risks and countermeasures
in both centralized and collaborative learning settings, this paper aims to
provide a thorough understanding of effective strategies for protecting ML
training data against privacy intrusions. It explores the balance between data
privacy and model utility, shedding light on privacy-preserving techniques that
leverage cryptographic methods, Differential Privacy, and Trusted Execution
Environments. The discussion extends to the application of these techniques in
sensitive domains, underscoring the critical role of PPML in ensuring the
privacy and security of ML systems.

探讨隐私保护机器学习（PPML）的兴起及其对各领域的巨大影响，强调在机器学习框架中保护隐私所面临的挑战，讨论当前研究努力，旨在最小化隐私敏感信息和增强数据处理技术，通过应用密码学方法、差分隐私和可信执行环境等隐私保护技术，保护机器学习训练数据防止隐私侵犯，尤其关注 PPML 在敏感领域中的应用及其在保护机器学习系统隐私与安全方面的关键作用。

提升机器学习数据隐私保护的最新方法 —— 综述

State-of-the-Art Approaches to Enhancing Privacy Preservation of Machine  Learning Datasets: A Survey

The rapid advancement and widespread use of large language models (LLMs) have
raised significant concerns regarding the potential leakage of personally
identifiable information (PII). These models are often trained on vast
quantities of web-collected data, which may inadvertently include sensitive
personal data. This paper presents ProPILE, a novel probing tool designed to
empower data subjects, or the owners of the PII, with awareness of potential
PII leakage in LLM-based services. ProPILE lets data subjects formulate prompts
based on their own PII to evaluate the level of privacy intrusion in LLMs. We
demonstrate its application on the OPT-1.3B model trained on the publicly
available Pile dataset. We show how hypothetical data subjects may assess the
likelihood of their PII being included in the Pile dataset being revealed.
ProPILE can also be leveraged by LLM service providers to effectively evaluate
their own levels of PII leakage with more powerful prompts specifically tuned
for their in-house models. This tool represents a pioneering step towards
empowering the data subjects for their awareness and control over their own
data on the web.

本文介绍了一种探测工具 ProPILE，由数据主体或 PII 所有者制定提示，评估基于 LLMs 的服务中 PII 泄漏的程度，并且展示了其在 OPT-1.3B 上的应用，该工具是授予数据主体他们对网络数据的知情权和控制权的开创性一步。