Overview

Machine unlearning asks how to remove a person’s data, a class, or a learned concept from a model after training, often to support privacy, safety, or changing data rights. Approaches range from exact or certified deletion methods, such as data partitioning and noisy or influence-based updates, to approximate parameter edits, representation changes, and inference-time steering; some systems are designed from the outset to make deletion easier. Researchers evaluate methods against retrained models and test forgetting, retained utility, privacy attacks, recovery, and repeated deletion across language, vision, diffusion, graph, and multimodal systems. A central tension is that suppressed outputs do not necessarily mean information is erased, while stronger removal can damage related knowledge; scalable methods with reliable guarantees and low collateral harm remain a challenge.

Latest papers

372 papers34 papers in the last four weeks, down 40% on the four weeks before. 0.2% of all new papers.

Jun 12, 2025

GUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models

Unlearning large language models (LLMs) is important due to copyright and privacy concerns. A key challenge is unintended forgetting, where removing data inadvertently impairs model utility. While prior work has focused on architectural innovations, the influence of data-level factors remains underexplored. We introduce GUARD, a framework for Guided Unlearning And Retention via Data Attribution. GUARD uses a lightweight proxy data attribution metric tailored to LLM unlearning, which efficiently quantifies the "alignment" between the Forget and Retain (or synthetic supplement) Sets. This metric leads to a new unlearning objective that assigns adaptive, nonuniform weights to samples, decaying exponentially with their proxy attribution scores, and thereby provably mitigates unintended retention loss. On the TOFU benchmark with a 10% forget set, applying GUARD to Gradient Ascent (GA) improves Retain Set ROUGE-L from 0.18 to 22.40 (a 124x increase) and Retain Probability from 0.06% to 17.50%, a substantial recovery from the GA collapse. Furthermore, GUARD combined with NPO (Negative Preference Optimization) outperforms Representation Misdirection for Unlearning (RMU) with 33.80% and 53.10% reductions in the Retain Set Sacrifice Rates computed from ROUGE-L and Probability (ρrρ_r and ρpρ_p), and a 16.01% improvement in knowledge retention on the MUSE NEWS Retain Set. These findings persist when attribution scores are computed using synthetic or highly subsampled (20%) Retain Sets, where NPO+GUARD still reduces ρrρ_r and ρpρ_p by up to 43.89% and 48.13% over NPO. Similar improvements are observed on MUSE, with a tolerable absolute privacy leakage degradation of 13.7 compared to the best-performing existing method in the privacy category.
Jun 5, 2025

UNO: Unlearning via Orthogonalization in Generative models

As generative models become increasingly powerful and pervasive, the ability to unlearn specific data due to privacy concerns, legal requirements, or harmful content has become increasingly important. Unlearning aims to selectively remove the influence of particular data without costly retraining from scratch. Effective unlearning requires (i) forgetting undesired data, (ii) preserving generation quality, (iii) retaining the influence of desired training data on model parameters, and (iv) computational efficiency. We propose fast unlearning algorithms based on loss gradient orthogonalization for unconditional and conditional generative models. We consider the loss function of the original model restricted to the retain data and augment it by a term promoting the orthogonality between the two gradients of the loss function evaluated at the retain dataset and the forget dataset. We coin this method unlearning via orthogonalization (UNO) and show that the additional weak orthogonality constraint accelerates unlearning. The inclusion of the weak orthogonality constraint implies that each gradient descent step utilizes local information about the geometry via the Hessian of the loss function. Our geometry aware gradient descent step significantly accelerates the learning of the retain data loss function compared to a gradient descent which uses only gradient information. By alternating between an UNO and a gradient surgery step, we obtain UNO-S, which further reduces execution time. We demonstrate that our algorithms effectively forget data while preserving the fidelity of the original model. On standard image benchmarks, they achieve orders-of-magnitude faster unlearning than existing methods such as gradient surgery. We validate our approach on datasets of increasing complexity (MNIST, CelebA, and ImageNet-1K) and generative architectures ranging from VAEs to diffusion transformers.
May 24, 2025

Safety Alignment via Constrained Knowledge Unlearning

Despite significant progress in safety alignment, large language models (LLMs) remain susceptible to jailbreak attacks. Existing defense mechanisms have not fully deleted harmful knowledge in LLMs, which allows such attacks to bypass safeguards and produce harmful outputs. To address this challenge, we propose a novel safety alignment strategy, Constrained Knowledge Unlearning (CKU), which focuses on two primary objectives: knowledge localization and retention, and unlearning harmful knowledge. CKU works by scoring neurons in specific multilayer perceptron (MLP) layers to identify a subset U of neurons associated with useful knowledge. During the unlearning process, CKU prunes the gradients of neurons in U to preserve valuable knowledge while effectively mitigating harmful content. Experimental results demonstrate that CKU significantly enhances model safety without compromising overall performance, offering a superior balance between safety and utility compared to existing methods. Additionally, our analysis of neuron knowledge sensitivity across various MLP layers provides valuable insights into the mechanics of safety alignment and model knowledge editing.
Apr 30, 2025

The Linear Geometry of Interpretable Tokens: Jailbreaking Attacks and Defenses for Unlearned Diffusion Models

Diffusion models excel at generating high-quality images but can memorize and reproduce harmful concepts when prompted. Although fine-tuning methods have been proposed to unlearn a target concept, they struggle to fully erase it while maintaining generation quality on other concepts, leaving models vulnerable to jailbreak attacks. Existing jailbreak methods demonstrate this vulnerability but offer limited insight into how unlearned models retain harmful concepts, limiting progress on effective defenses. In this work, we show that a coherent, interpretable, attack-accessible linear residual of the erased concept can be recovered in the token embedding space, and that both an attack and a defense follow from this structure. We introduce SubAttack, a novel jailbreaking attack that reads out this subspace by learning an orthogonal set of attack token embeddings, each being a linear combination of human-interpretable textual elements, revealing that unlearned models still retain the target concept through related textual components. Furthermore, our attack is also more powerful and transferable across text prompts, initial noises, and unlearned models than prior attacks. Conversely, projecting out the same subspace yields SubDefense, a lightweight plug-and-play defense mechanism that suppresses the residual concept in unlearned models. SubDefense provides stronger robustness than existing defenses while better preserving safe generation quality. Extensive experiments across multiple unlearning methods, concepts, and attack types demonstrate that our approach advances both understanding and mitigation of vulnerabilities in diffusion unlearning.
Apr 11, 2025

SAEs Can Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs

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 Dynamic DAE Guardrails\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.
Apr 6, 2025

Exact Unlearning of Finetuning Data via Model Merging at Scale

Approximate unlearning has gained popularity as an approach to efficiently update an LLM so that it behaves (roughly) as if it was not trained on a subset of data to begin with. However, existing methods are brittle in practice and can easily be attacked to reveal supposedly unlearned information. To alleviate issues with approximate unlearning, we instead propose SIFT-Masks (SIgn-Fixed Tuning-Masks), an exact unlearning method based on model merging. SIFT-Masks addresses two key limitations of standard model merging: (1) merging a large number of tasks can severely harm utility; and (2) methods that boost utility by sharing extra information across tasks make exact unlearning prohibitively expensive. SIFT-Masks solves these issues by (1) applying local masks to recover task-specific performance; and (2) constraining finetuning to align with a global sign vector as a lightweight approach to determine masks independently before merging. Across four settings where we merge up to 500 models, SIFT-Masks improves accuracy by 5-80% over naive merging and uses up to 250x less compute for exact unlearning compared to other merging baselines.
Feb 8, 2025

Machine Unlearning via Information Theoretic Regularization

How can we effectively remove or ``unlearn'' undesirable information, such as specific features or the influence of individual data points, from a learning outcome while minimizing utility loss and ensuring rigorous guarantees? We introduce a unified mathematical framework based on information-theoretic regularization to address both data-point unlearning and feature unlearning. For data-point unlearning, we introduce the Marginal Unlearning Principle, an auditable and provable framework. Moreover, we provide an information-theoretic unlearning definition based on the proposed principle and provable guarantees on sufficiency and necessity of marginal unlearning. We then show that the proposed framework provides a natural solution to the marginal unlearning problem and yields auditable high-probability marginal-unlearning guarantees. For feature unlearning, the framework applies to deep learning with flexible training objectives. By combining flexibility in learning objectives with simplicity in regularization design, our approach is highly adaptable and practical for a wide range of machine learning and AI applications. From a mathematical perspective, we provide a unified analytic solution to the optimal feature unlearning problem with a variety of information-theoretic training objectives. Our theoretical analysis reveals intriguing connections between machine unlearning, information theory, optimal transport, and extremal sigma algebras. Numerical simulations support our theoretical findings.
Dec 12, 2024

The Utility and Complexity of in- and out-of-Distribution Machine Unlearning

Machine unlearning, the process of selectively removing data from trained models, is increasingly crucial for addressing privacy concerns and knowledge gaps post-deployment. Despite this importance, existing approaches are often heuristic and lack formal guarantees. In this paper, we analyze the fundamental utility, time, and space complexity trade-offs of approximate unlearning, providing rigorous certification analogous to differential privacy. For in-distribution forget data -- data similar to the retain set -- we show that a surprisingly simple and general procedure, empirical risk minimization with output perturbation, achieves tight unlearning-utility-complexity trade-offs, addressing a previous theoretical gap on the separation from unlearning "for free" via differential privacy, which inherently facilitates the removal of such data. However, such techniques fail with out-of-distribution forget data -- data significantly different from the retain set -- where unlearning time complexity can exceed that of retraining, even for a single sample. To address this, we propose a new robust and noisy gradient descent variant that provably amortizes unlearning time complexity without compromising utility.
Oct 3, 2024

Instance-Level Difficulty: A Missing Perspective in Machine Unlearning

Current research on deep machine unlearning primarily focuses on improving or evaluating the overall effectiveness of unlearning methods while overlooking the varying difficulty of unlearning individual training samples. As a result, the broader feasibility of machine unlearning remains under-explored. This paper studies the cruxes that make machine unlearning difficult through a thorough instance-level unlearning performance analysis over various unlearning algorithms and datasets. In particular, we summarize four factors that make unlearning a data point difficult, and we empirically show that these factors are independent of a specific unlearning algorithm but only relevant to the target model and its training data. Given these findings, we argue that machine unlearning research should pay attention to the instance-level difficulty of unlearning.
May 24, 2024

Class Machine Unlearning for Complex Data via Concepts Inference and Data Poisoning

Machine unlearning aims to remove the influence of specified training data or knowledge from a trained model without requiring full retraining. This capability is particularly important for modern image classifiers and large language models (LLMs), where retraining can be computationally expensive. However, machine unlearning on complex data remains difficult because the target information is often distributed across multiple semantic elements. Existing methods mainly remove samples, modify labels, or edit model parameters to reduce the influence of the forgetting target. These approaches usually do not explicitly identify which semantic concepts connect the forgetting target to the model's prediction or generated response. As a result, it is difficult to determine which information to modify. This uncertainty may leave residual target information or unnecessarily affect knowledge that should be retained. To address this gap, we propose a concept-guided poisoning unlearning framework that explicitly identifies the concepts that contribute most strongly to the target class or knowledge and uses them to guide the model update. For image classification, our method first identifies class-relevant concepts with a Post-hoc Concept Bottleneck Model, localizes the image regions that express these concepts, and constructs replacement-based poisoned samples. For LLMs, it elicits the target knowledge through multiple questions, aggregates Integrated Gradients across the resulting responses to identify consistently important content, and masks this content to construct poisoned training targets. Experiments on multiple datasets show that the proposed framework achieves effective unlearning across different tasks while largely preserving retained model utility.
Apr 8, 2024

Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge

Jailbreaking attacks can enable Large Language Models (LLMs) to bypass the safeguard and generate harmful content. Existing jailbreaking defense methods have failed to address the fundamental issue that harmful knowledge resides within the model, leading to potential jailbreak risks for LLMs. In this paper, we propose a novel defense method called Eraser, which mainly includes three goals: unlearning harmful knowledge, retaining general knowledge, and maintaining safety alignment. The intuition is that if an LLM forgets the specific knowledge required to answer a harmful question, it will no longer have the ability to answer harmful questions. The training of Erase does not actually require the model's own harmful knowledge, and it can benefit from unlearning general answers related to harmful queries, which means it does not need assistance from the red team. The experimental results show that Eraser can significantly reduce the jailbreaking success rate for various attacks without compromising the general capabilities of the model. Our codes are available at https://github.com/ZeroNLP/Eraser.
Dec 9, 2023

Generalized Influence Functions for Better Model Change Estimates

Influence functions (IFs) approximate the effect of removing or reweighting training data on a trained model, but their linear approximation often lacks the accuracy required for reliable post hoc model editing. We identify two culprits and propose generalized influence functions (GIFs) and pseudo-LiSSA (p-LiSSA) to address each in turn. First, classical IFs update all parameters indiscriminately, leading to unnecessary updates to data-irrelevant parameters. GIFs instead restrict edits to a data-relevant subspace and leave the remaining parameters fixed. We theoretically show that GIFs achieve a tighter error bound than classical IFs when the parameter subset is properly selected, and that effective subspace selection requires avoiding low-curvature directions while retaining a sufficiently large component of the target gradient. Second, LiSSA iterations are destabilized by negative Hessian eigenvalues, which existing methods handle via ℓ2\ell_2 damping, at the cost of a biased inverse-Hessian-vector product (iHVP) estimate. p-LiSSA eliminates this bias by solving the restricted inverse-Hessian problem without such damping. We further show that the presence of low-curvature directions slows p-LiSSA convergence, and that the data-relevant subspace selected by GIFs mitigates this. Across five image and text unlearning benchmarks, GIFs update only 10% of the parameters yet preserve accuracy up to 2.12 percentage points better than IF-based baselines, while improving unlearning performance by up to 2.73 percentage points. Moreover, p-LiSSA improves restricted iHVP estimation by reducing the residual by 9.6×\times over existing iHVP baselines, while using 19.8% less memory with comparable computation time. Code is available at https://github.com/hslyu/GIF.