Data-Free Privacy-Preserving for LLMs via Model Inversion and Selective Unlearning

• URL: http://arxiv.org/abs/2601.15595v1
• Date: Thu, 22 Jan 2026 02:43:12 GMT
• Title: Data-Free Privacy-Preserving for LLMs via Model Inversion and Selective Unlearning
• Authors: Xinjie Zhou, Zhihui Yang, Lechao Cheng, Sai Wu, Gang Chen,
• Abstract summary: Large language models (LLMs) exhibit powerful capabilities but risk memorizing sensitive personally identifiable information (PII) from their training data.<n>We propose Data-Free Selective Unlearning (DFSU), a novel privacy-preserving framework that removes sensitive PII from an LLM without requiring its training data.<n>Our approach first synthesizes pseudo-PII through language model inversion, then constructs token-level privacy masks for these synthetic samples, and finally performs token-level selective unlearning.
• Score: 27.452191507918148
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) exhibit powerful capabilities but risk memorizing sensitive personally identifiable information (PII) from their training data, posing significant privacy concerns. While machine unlearning techniques aim to remove such data, they predominantly depend on access to the training data. This requirement is often impractical, as training data in real-world deployments is commonly proprietary or inaccessible. To address this limitation, we propose Data-Free Selective Unlearning (DFSU), a novel privacy-preserving framework that removes sensitive PII from an LLM without requiring its training data. Our approach first synthesizes pseudo-PII through language model inversion, then constructs token-level privacy masks for these synthetic samples, and finally performs token-level selective unlearning via a contrastive mask loss within a low-rank adaptation (LoRA) subspace. Extensive experiments on the AI4Privacy PII-Masking dataset using Pythia models demonstrate that our method effectively removes target PII while maintaining model utility.

Related papers

• Rendering Data Unlearnable by Exploiting LLM Alignment Mechanisms [3.648393062009244]
  Large language models (LLMs) are increasingly trained on massive, heterogeneous text corpora.<n>This raises serious concerns about the unauthorised use of proprietary or personal data during model training.<n>We propose Disclaimer Injection, a novel data-level defence that renders text unlearnable to LLMs.
  arXiv  Detail & Related papers  (2026-01-06T20:34:15Z)
• Game-Theoretic Machine Unlearning: Mitigating Extra Privacy Leakage [12.737028324709609]
  Recent legislation obligates organizations to remove requested data and its influence from a trained model. We propose a game-theoretic machine unlearning algorithm that simulates the competitive relationship between unlearning performance and privacy protection.
  arXiv  Detail & Related papers  (2024-11-06T13:47:04Z)
• Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models [52.40798352740857]
  We introduce the Iterative Contrastive Unlearning (ICU) framework, which consists of three core components.<n>A Knowledge Unlearning Induction module targets specific knowledge for removal using an unlearning loss.<n>A Contrastive Learning Enhancement module preserves the model's expressive capabilities against the pure unlearning goal.<n>An Iterative Unlearning Refinement module dynamically adjusts the unlearning process through ongoing evaluation and updates.
  arXiv  Detail & Related papers  (2024-07-25T07:09:35Z)
• Learning to Refuse: Towards Mitigating Privacy Risks in LLMs [6.685921135304385]
  Large language models (LLMs) exhibit remarkable capabilities in understanding and generating natural language. This study addresses the challenge of enabling LLMs to protect specific individuals' private data without the need for complete retraining. We introduce the Name-Aware Unlearning Framework (NAUF) for Privacy Protection, which enables the model to learn which individuals' information should be protected.
  arXiv  Detail & Related papers  (2024-07-14T03:05:53Z)
• The Frontier of Data Erasure: Machine Unlearning for Large Language Models [56.26002631481726]
  Large Language Models (LLMs) are foundational to AI advancements. LLMs pose risks by potentially memorizing and disseminating sensitive, biased, or copyrighted information. Machine unlearning emerges as a cutting-edge solution to mitigate these concerns.
  arXiv  Detail & Related papers  (2024-03-23T09:26:15Z)
• Unlearn What You Want to Forget: Efficient Unlearning for LLMs [92.51670143929056]
  Large language models (LLMs) have achieved significant progress from pre-training on and memorizing a wide range of textual data. This process might suffer from privacy issues and violations of data protection regulations. We propose an efficient unlearning framework that could efficiently update LLMs without having to retrain the whole model after data removals.
  arXiv  Detail & Related papers  (2023-10-31T03:35:59Z)
• 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)
• Recovering from Privacy-Preserving Masking with Large Language Models [14.828717714653779]
  We use large language models (LLMs) to suggest substitutes of masked tokens. We show that models trained on the obfuscation corpora are able to achieve comparable performance with the ones trained on the original data.
  arXiv  Detail & Related papers  (2023-09-12T16:39:41Z)
• Privacy Side Channels in Machine Learning Systems [87.53240071195168]
  We introduce privacy side channels: attacks that exploit system-level components to extract private information. For example, we show that deduplicating training data before applying differentially-private training creates a side-channel that completely invalidates any provable privacy guarantees. We further show that systems which block language models from regenerating training data can be exploited to exfiltrate private keys contained in the training set.
  arXiv  Detail & Related papers  (2023-09-11T16:49:05Z)
• Just Fine-tune Twice: Selective Differential Privacy for Large Language Models [69.66654761324702]
  We propose a simple yet effective just-fine-tune-twice privacy mechanism to achieve SDP for large Transformer-based language models. Experiments show that our models achieve strong performance while staying robust to the canary insertion attack.
  arXiv  Detail & Related papers  (2022-04-15T22:36:55Z)

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.