SAEs $\textit{Can}$ Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs

• URL: http://arxiv.org/abs/2504.08192v1
• Date: Fri, 11 Apr 2025 01:24:03 GMT
• Title: SAEs $\textit{Can}$ Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs
• Authors: Aashiq Muhamed, Jacopo Bonato, Mona Diab, Virginia Smith,
• Abstract summary: We introduce $textbfDynamic DAE Guardrails$ (DSG), a novel method for precision unlearning.<n>Our experiments show DSG substantially outperforms leading unlearning methods.
• Score: 24.48560556882878
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine unlearning is a promising approach to improve LLM safety by removing unwanted knowledge from the model. However, prevailing gradient-based unlearning methods suffer from issues such as high computational costs, hyperparameter instability, poor sequential unlearning capability, vulnerability to relearning attacks, low data efficiency, and lack of interpretability. While Sparse Autoencoders are well-suited to improve these aspects by enabling targeted activation-based unlearning, prior approaches underperform gradient-based methods. This work demonstrates that, contrary to these earlier findings, SAEs can significantly improve unlearning when employed dynamically. We introduce $\textbf{Dynamic DAE Guardrails}$ (DSG), a novel method for precision unlearning that leverages principled feature selection and a dynamic classifier. Our experiments show DSG substantially outperforms leading unlearning methods, achieving superior forget-utility trade-offs. DSG addresses key drawbacks of gradient-based approaches for unlearning -- offering enhanced computational efficiency and stability, robust performance in sequential unlearning, stronger resistance to relearning attacks, better data efficiency including zero-shot settings, and more interpretable unlearning.

Related papers

• Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond [41.3029262040131]
  We investigate how to make unlearned models robust against relearning attacks.<n>Our analysis reveals that smoothness optimization plays a pivotal role in mitigating relearning attacks.
  arXiv  Detail & Related papers  (2025-02-07T23:03:55Z)
• 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. This poses risk of privacy and copyright violations, highlighting the need for efficient machine unlearning methods. 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)
• 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)
• UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models [12.45822383965784]
  We introduce UnDIAL (Unlearning via Self-Distillation on Adjusted Logits), a novel and robust unlearning method. Our approach leverages self-distillation to adjust logits and selectively reduce the influence of targeted tokens.
  arXiv  Detail & Related papers  (2024-02-15T16:21:14Z)
• 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)
• Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening [51.34904967046097]
  Selective Synaptic Dampening (SSD) is a fast, performant, and does not require long-term storage of the training data. We present a novel two-step, post hoc, retrain-free approach to machine unlearning which is fast, performant, and does not require long-term storage of the training data.
  arXiv  Detail & Related papers  (2023-08-15T11:30:45Z)
• Robust Learning with Progressive Data Expansion Against Spurious Correlation [65.83104529677234]
  We study the learning process of a two-layer nonlinear convolutional neural network in the presence of spurious features. Our analysis suggests that imbalanced data groups and easily learnable spurious features can lead to the dominance of spurious features during the learning process. We propose a new training algorithm called PDE that efficiently enhances the model's robustness for a better worst-group performance.
  arXiv  Detail & Related papers  (2023-06-08T05:44:06Z)
• 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)
• Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting [66.45372974713189]
  We propose a recall and learn mechanism, which adopts the idea of multi-task learning and jointly learns pretraining tasks and downstream tasks. Experiments show that our method achieves state-of-the-art performance on the GLUE benchmark. We provide open-source RecAdam, which integrates the proposed mechanisms into Adam to facility the NLP community.
  arXiv  Detail & Related papers  (2020-04-27T08:59:57Z)

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.