Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection

• URL: http://arxiv.org/abs/2508.15449v1
• Date: Thu, 21 Aug 2025 11:12:09 GMT
• Title: Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection
• Authors: Chengcan Wu, Zeming Wei, Huanran Chen, Yinpeng Dong, Meng Sun,
• Abstract summary: We propose a Metamorphosis Representation Projection (MRP) approach to machine unlearning.<n>By implementing projective transformations in the hidden state space of specific network layers, our method effectively eliminates harmful information while preserving useful knowledge.<n> Experimental results demonstrate that our approach enables effective continuous unlearning and successfully defends against relearning attacks.
• Score: 17.369869625390894
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While Large Language Models (LLMs) have demonstrated impressive performance in various domains and tasks, concerns about their safety are becoming increasingly severe. In particular, since models may store unsafe knowledge internally, machine unlearning has emerged as a representative paradigm to ensure model safety. Existing approaches employ various training techniques, such as gradient ascent and negative preference optimization, in attempts to eliminate the influence of undesired data on target models. However, these methods merely suppress the activation of undesired data through parametric training without completely eradicating its informational traces within the model. This fundamental limitation makes it difficult to achieve effective continuous unlearning, rendering these methods vulnerable to relearning attacks. To overcome these challenges, we propose a Metamorphosis Representation Projection (MRP) approach that pioneers the application of irreversible projection properties to machine unlearning. By implementing projective transformations in the hidden state space of specific network layers, our method effectively eliminates harmful information while preserving useful knowledge. Experimental results demonstrate that our approach enables effective continuous unlearning and successfully defends against relearning attacks, achieving state-of-the-art performance in unlearning effectiveness while preserving natural performance. Our code is available in https://github.com/ChengcanWu/MRP.

Related papers

• Sparsity-Aware Unlearning for Large Language Models [20.699929903336113]
  Large Language Models (LLMs) inevitably memorize sensitive information during training, posing significant privacy risks.<n>Machine unlearning has emerged as a promising solution to selectively remove such information without full retraining.<n>We find that unlearning effectiveness degrades substantially on sparse models.<n>We propose Sparsity-Aware Unlearning (SAU), which decouples unlearning from sparsification objectives through gradient masking.
  arXiv  Detail & Related papers  (2026-01-31T07:45:30Z)
• 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)
• Forgetting-MarI: LLM Unlearning via Marginal Information Regularization [6.979586479353831]
  Existing unlearning methods often degrade model performance by removing more information than necessary when attempting to ''forget'' specific data.<n>We introduce Forgetting-MarI, an LLM unlearning framework that provably removes only the additional (marginal) information contributed by the data to be unlearned.<n>By penalizing marginal information, our method yields an explicit upper bound on the unlearn dataset's residual influence in the trained models, providing provable undetectability.
  arXiv  Detail & Related papers  (2025-11-14T22:48:39Z)
• Dissecting Fine-Tuning Unlearning in Large Language Models [12.749301272512222]
  Fine-tuning-based unlearning methods prevail for preventing harmful, sensitive, or copyrighted information within large language models. However, the true effectiveness of these methods is unclear. In this work, we delve into the limitations of fine-tuning-based unlearning through activation patching and restoration experiments.
  arXiv  Detail & Related papers  (2024-10-09T06:58:09Z)
• 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)
• 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)
• Silver Linings in the Shadows: Harnessing Membership Inference for Machine Unlearning [7.557226714828334]
  We present a novel unlearning mechanism designed to remove the impact of specific data samples from a neural network. In achieving this goal, we crafted a novel loss function tailored to eliminate privacy-sensitive information from weights and activation values of the target model. Our results showcase the superior performance of our approach in terms of unlearning efficacy and latency as well as the fidelity of the primary task.
  arXiv  Detail & Related papers  (2024-07-01T00:20:26Z)
• Machine Unlearning with Minimal Gradient Dependence for High Unlearning Ratios [18.73206066109299]
  Mini-Unlearning is a novel approach that capitalizes on a critical observation: unlearned parameters correlate with retrained parameters through contraction mapping. This lightweight, scalable method significantly enhances model accuracy and strengthens resistance to membership inference attacks. Our experiments demonstrate that Mini-Unlearning not only works under higher unlearning ratios but also outperforms existing techniques in both accuracy and security.
  arXiv  Detail & Related papers  (2024-06-24T01:43:30Z)
• Towards Effective Evaluations and Comparisons for LLM Unlearning Methods [97.2995389188179]
  This paper seeks to refine the evaluation of machine unlearning for large language models.<n>It addresses two key challenges -- the robustness of evaluation metrics and the trade-offs between competing goals.
  arXiv  Detail & Related papers  (2024-06-13T14:41:00Z)
• Unlearning Backdoor Attacks through Gradient-Based Model Pruning [10.801476967873173]
  We propose a novel approach to counter backdoor attacks by treating their mitigation as an unlearning task. Our approach offers simplicity and effectiveness, rendering it well-suited for scenarios with limited data availability.
  arXiv  Detail & Related papers  (2024-05-07T00:36:56Z)
• 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)
• Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection [56.292071534857946]
  Recent data-privacy laws have sparked interest in machine unlearning. Challenge is to discard information about the forget'' data without altering knowledge about remaining dataset. We adopt a projected-gradient based learning method, named as Projected-Gradient Unlearning (PGU) We provide empirically evidence to demonstrate that our unlearning method can produce models that behave similar to models retrained from scratch across various metrics even when the training dataset is no longer accessible.
  arXiv  Detail & Related papers  (2023-12-07T07:17:24Z)
• 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)
• Segue: Side-information Guided Generative Unlearnable Examples for Facial Privacy Protection in Real World [64.4289385463226]
  We propose Segue: Side-information guided generative unlearnable examples. To improve transferability, we introduce side information such as true labels and pseudo labels. It can resist JPEG compression, adversarial training, and some standard data augmentations.
  arXiv  Detail & Related papers  (2023-10-24T06:22:37Z)
• Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources [78.72922528736011]
  We propose a novel approach, black-box adversarial reprogramming (BAR), that repurposes a well-trained black-box machine learning model. Using zeroth order optimization and multi-label mapping techniques, BAR can reprogram a black-box ML model solely based on its input-output responses. BAR outperforms state-of-the-art methods and yields comparable performance to the vanilla adversarial reprogramming method.
  arXiv  Detail & Related papers  (2020-07-17T01:52:34Z)

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.