Towards Benchmarking Privacy Vulnerabilities in Selective Forgetting with Large Language Models

• URL: http://arxiv.org/abs/2512.18035v1
• Date: Fri, 19 Dec 2025 20:04:06 GMT
• Title: Towards Benchmarking Privacy Vulnerabilities in Selective Forgetting with Large Language Models
• Authors: Wei Qian, Chenxu Zhao, Yangyi Li, Mengdi Huai,
• Abstract summary: selective forgetting (also known as machine unlearning) has shown promise for privacy and data removal tasks.<n>Despite its promise, selective forgetting raises significant privacy concerns.<n>We present the first comprehensive benchmark for evaluating privacy vulnerabilities in selective forgetting.
• Score: 28.389198065125314
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid advancements in artificial intelligence (AI) have primarily focused on the process of learning from data to acquire knowledgeable learning systems. As these systems are increasingly deployed in critical areas, ensuring their privacy and alignment with human values is paramount. Recently, selective forgetting (also known as machine unlearning) has shown promise for privacy and data removal tasks, and has emerged as a transformative paradigm shift in the field of AI. It refers to the ability of a model to selectively erase the influence of previously seen data, which is especially important for compliance with modern data protection regulations and for aligning models with human values. Despite its promise, selective forgetting raises significant privacy concerns, especially when the data involved come from sensitive domains. While new unlearning-induced privacy attacks are continuously proposed, each is shown to outperform its predecessors using different experimental settings, which can lead to overly optimistic and potentially unfair assessments that may disproportionately favor one particular attack over the others. In this work, we present the first comprehensive benchmark for evaluating privacy vulnerabilities in selective forgetting. We extensively investigate privacy vulnerabilities of machine unlearning techniques and benchmark privacy leakage across a wide range of victim data, state-of-the-art unlearning privacy attacks, unlearning methods, and model architectures. We systematically evaluate and identify critical factors related to unlearning-induced privacy leakage. With our novel insights, we aim to provide a standardized tool for practitioners seeking to deploy customized unlearning applications with faithful privacy assessments.

Related papers

• Unintended Memorization of Sensitive Information in Fine-Tuned Language Models [24.228889351240838]
  Fine-tuning Large Language Models (LLMs) on sensitive datasets carries a substantial risk of unintended memorization and leakage of Personally Identifiable Information (PII)<n>We design controlled extraction probes to quantify unintended PII memorization and study how factors such as language, PII frequency, task type, and model size influence memorization behavior.
  arXiv  Detail & Related papers  (2026-01-24T15:08:45Z)
• Differential Privacy in Machine Learning: From Symbolic AI to LLMs [49.1574468325115]
  Differential privacy provides a formal framework to mitigate privacy risks.<n>It ensures that the inclusion or exclusion of any single data point does not significantly alter the output of an algorithm.
  arXiv  Detail & Related papers  (2025-06-13T11:30:35Z)
• Privacy in Fine-tuning Large Language Models: Attacks, Defenses, and Future Directions [11.338466798715906]
  Fine-tuning Large Language Models (LLMs) can achieve state-of-the-art performance across various domains.<n>This paper provides a comprehensive survey of privacy challenges associated with fine-tuning LLMs.<n>We highlight vulnerabilities to various privacy attacks, including membership inference, data extraction, and backdoor attacks.
  arXiv  Detail & Related papers  (2024-12-21T06:41:29Z)
• Footprints of Data in a Classifier: Understanding the Privacy Risks and Solution Strategies [0.9208007322096533]
  Article 17 of the General Data Protection Regulation (Right Erasure) requires data to be permanently removed from a system to prevent potential compromise.<n>One such issue arises from the residual footprints of training data embedded within predictive models.<n>This study examines how two fundamental aspects of classifier systems - training quality and classifier training methodology - contribute to privacy vulnerabilities.
  arXiv  Detail & Related papers  (2024-07-02T13:56:37Z)
• PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners [81.571305826793]
  We introduce Contextual Privacy Protection Language Models (PrivacyMind) Our work offers a theoretical analysis for model design and benchmarks various techniques. In particular, instruction tuning with both positive and negative examples stands out as a promising method.
  arXiv  Detail & Related papers  (2023-10-03T22:37:01Z)
• A Unified View of Differentially Private Deep Generative Modeling [60.72161965018005]
  Data with privacy concerns comes with stringent regulations that frequently prohibited data access and data sharing. Overcoming these obstacles is key for technological progress in many real-world application scenarios that involve privacy sensitive data. Differentially private (DP) data publishing provides a compelling solution, where only a sanitized form of the data is publicly released.
  arXiv  Detail & Related papers  (2023-09-27T14:38:16Z)
• On the Privacy Effect of Data Enhancement via the Lens of Memorization [20.63044895680223]
  We propose to investigate privacy from a new perspective called memorization. Through the lens of memorization, we find that previously deployed MIAs produce misleading results as they are less likely to identify samples with higher privacy risks. We demonstrate that the generalization gap and privacy leakage are less correlated than those of the previous results.
  arXiv  Detail & Related papers  (2022-08-17T13:02:17Z)
• SF-PATE: Scalable, Fair, and Private Aggregation of Teacher Ensembles [50.90773979394264]
  This paper studies a model that protects the privacy of individuals' sensitive information while also allowing it to learn non-discriminatory predictors. A key characteristic of the proposed model is to enable the adoption of off-the-selves and non-private fair models to create a privacy-preserving and fair model.
  arXiv  Detail & Related papers  (2022-04-11T14:42:54Z)
• Towards a Data Privacy-Predictive Performance Trade-off [2.580765958706854]
  We evaluate the existence of a trade-off between data privacy and predictive performance in classification tasks. Unlike previous literature, we confirm that the higher the level of privacy, the higher the impact on predictive performance.
  arXiv  Detail & Related papers  (2022-01-13T21:48:51Z)
• Trustworthy AI [75.99046162669997]
  Brittleness to minor adversarial changes in the input data, ability to explain the decisions, address the bias in their training data, are some of the most prominent limitations. We propose the tutorial on Trustworthy AI to address six critical issues in enhancing user and public trust in AI systems.
  arXiv  Detail & Related papers  (2020-11-02T20:04:18Z)
• Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach [54.32266555843765]
  This paper studies a model that protects the privacy of the individuals sensitive information while also allowing it to learn non-discriminatory predictors. The method relies on the notion of differential privacy and the use of Lagrangian duality to design neural networks that can accommodate fairness constraints.
  arXiv  Detail & Related papers  (2020-09-26T10:50:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.