Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy

• URL: http://arxiv.org/abs/2506.00359v1
• Date: Sat, 31 May 2025 02:57:24 GMT
• Title: Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
• Authors: Jie Ren, Zhenwei Dai, Xianfeng Tang, Yue Xing, Shenglai Zeng, Hui Liu, Jingying Zeng, Qiankun Peng, Samarth Varshney, Suhang Wang, Qi He, Charu C. Aggarwal, Hui Liu,
• Abstract summary: This paper reveals a critical vulnerability in fine-tuning-based unlearning.<n>A malicious user can craft a manipulated forgetting request that stealthily degrades the model's utility for benign users.<n>We propose Scope-aware Unlearning (SU), a lightweight enhancement that introduces a scope term into the unlearning objective.
• Score: 36.19634262653306
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks, growing concerns have emerged over the misuse of sensitive, copyrighted, or harmful data during training. To address these concerns, unlearning techniques have been developed to remove the influence of specific data without retraining from scratch. However, this paper reveals a critical vulnerability in fine-tuning-based unlearning: a malicious user can craft a manipulated forgetting request that stealthily degrades the model's utility for benign users. We demonstrate this risk through a red-teaming Stealthy Attack (SA), which is inspired by two key limitations of existing unlearning (the inability to constrain the scope of unlearning effect and the failure to distinguish benign tokens from unlearning signals). Prior work has shown that unlearned models tend to memorize forgetting data as unlearning signals, and respond with hallucinations or feigned ignorance when unlearning signals appear in the input. By subtly increasing the presence of common benign tokens in the forgetting data, SA enhances the connection between benign tokens and unlearning signals. As a result, when normal users include such tokens in their prompts, the model exhibits unlearning behaviors, leading to unintended utility degradation. To address this vulnerability, we propose Scope-aware Unlearning (SU), a lightweight enhancement that introduces a scope term into the unlearning objective, encouraging the model to localize the forgetting effect. Our method requires no additional data processing, integrates seamlessly with existing fine-tuning frameworks, and significantly improves robustness against SA. Extensive experiments validate the effectiveness of both SA and SU.

Related papers

• UniErase: Unlearning Token as a Universal Erasure Primitive for Language Models [54.75551043657238]
  We introduce UniErase, a novel unlearning paradigm that employs learnable parametric suffix (unlearning token) to steer language models toward targeted forgetting behaviors.<n>UniErase achieves state-of-the-art (SOTA) performance across batch, sequential, and precise unlearning under fictitious and real-world knowledge settings.
  arXiv  Detail & Related papers  (2025-05-21T15:53:28Z)
• GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection [36.38245533018162]
  Large Language Models (LLMs) have demonstrated strong capabilities in memorizing vast amounts of knowledge across diverse domains.<n>Existing unlearning efforts typically fine-tune the model with resources such as forget data, retain data, and a calibration model.<n>We propose Generation-time Unlearning via Adaptive Restriction and Detection (GUARD), a framework that enables dynamic unlearning during LLM generation.
  arXiv  Detail & Related papers  (2025-05-19T16:26:58Z)
• Improving LLM Unlearning Robustness via Random Perturbations [6.287449249401005]
  We show that current state-of-the-art LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is in the retain-query.<n>To mitigate this vulnerability, we propose Random Noise Augmentation (RNA) -- a plug-and-play, model and method agnostic approach with theoretical guarantees for improving the robustness of unlearned models.
  arXiv  Detail & Related papers  (2025-01-31T15:12:20Z)
• Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models [19.015202590038996]
  We design Dynamic Unlearning Attack (DUA), a dynamic and automated framework to attack unlearned models. We propose Latent Adrial Unlearning (LAU), a universal framework that effectively enhances the robustness of the unlearned process. We demonstrate that LAU improves unlearning effectiveness by over $53.5%$, cause only less than a $11.6%$ reduction in neighboring knowledge, and have almost no impact on the model's general capabilities.
  arXiv  Detail & Related papers  (2024-08-20T09:36:04Z)
• Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs [25.91643745340183]
  Large Language Models (LLMs) have demonstrated strong reasoning and memorization capabilities via pretraining on massive textual corpora.<n>This poses risk of privacy and copyright violations, highlighting the need for efficient machine unlearning methods.<n>We propose Low-rank Knowledge Unlearning (LoKU), a novel framework that enables robust and efficient unlearning for LLMs.
  arXiv  Detail & Related papers  (2024-08-13T04:18:32Z)
• Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models [52.03511469562013]
  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)
• On Large Language Model Continual Unlearning [35.49718871265512]
  Machine unlearning has emerged as a representative approach for model safety and security.<n>These methods do not sufficiently consider that unlearning requests in real-world scenarios are continuously emerging.<n>We propose an Orthogonal low-rank adapter (LoRA) for continually unlearning requested data and an Out-Of-Distribution detector to measure the similarity between input and unlearning data.
  arXiv  Detail & Related papers  (2024-07-14T14:26:17Z)
• UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI [50.61495097098296]
  We revisit the paradigm in which unlearning is used for Large Language Models (LLMs) We introduce a concept of ununlearning, where unlearned knowledge gets reintroduced in-context. We argue that content filtering for impermissible knowledge will be required and even exact unlearning schemes are not enough for effective content regulation.
  arXiv  Detail & Related papers  (2024-06-27T10:24:35Z)
• Offset Unlearning for Large Language Models [49.851093293780615]
  delta-Unlearning is an offset unlearning framework for black-box LLMs.<n>We show that delta-Unlearning can effectively unlearn target data while maintaining similar or even stronger performance on general out-of-forget-scope tasks.
  arXiv  Detail & Related papers  (2024-04-17T03:39:51Z)
• 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)
• Machine Unlearning of Features and Labels [72.81914952849334]
  We propose first scenarios for unlearning and labels in machine learning models. Our approach builds on the concept of influence functions and realizes unlearning through closed-form updates of model parameters.
  arXiv  Detail & Related papers  (2021-08-26T04:42:24Z)

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.