With the surge and widespread application of image generation models, data privacy and content safety have become major concerns and attracted great attention from users, service providers, and policymakers. Machine unlearning (MU) is recognized as a cost-effective and promising means to address these challenges. Despite some advancements, image generation model unlearning (IGMU) still faces remarkable gaps in practice, e.g., unclear task discrimination and unlearning guidelines, lack of an effective evaluation framework, and unreliable evaluation metrics. These can hinder the understanding of unlearning mechanisms and the design of practical unlearning algorithms. We perform exhaustive assessments over existing state-of-the-art unlearning algorithms and evaluation standards, and discover several critical flaws and challenges in IGMU tasks. Driven by these limitations, we make several core contributions, to facilitate the comprehensive understanding, standardized categorization, and reliable evaluation of IGMU. Specifically, (1) We design CatIGMU, a novel hierarchical task categorization framework. It provides detailed implementation guidance for IGMU, assisting in the design of unlearning algorithms and the construction of testbeds. (2) We introduce EvalIGMU, a comprehensive evaluation framework. It includes reliable quantitative metrics across five critical aspects. (3) We construct DataIGM, a high-quality unlearning dataset, which can be used for extensive evaluations of IGMU, training content detectors for judgment, and benchmarking the state-of-the-art unlearning algorithms. With EvalIGMU and DataIGM, we discover that most existing IGMU algorithms cannot handle the unlearning well across different evaluation dimensions, especially for preservation and robustness. Code and models are available at https://github.com/ryliu68/IGMU.
Large Language Models (LLMs) offer transformative capabilities for hardware design automation, particularly in Verilog code generation. However, they also pose significant data security challenges, including Verilog evaluation data contamination, intellectual property (IP) design leakage, and the risk of malicious Verilog generation. We introduce SALAD, a comprehensive assessment that leverages machine unlearning to mitigate these threats. Our approach enables the selective removal of contaminated benchmarks, sensitive IP and design artifacts, or malicious code patterns from pre-trained LLMs, all without requiring full retraining. Through detailed case studies, we demonstrate how machine unlearning techniques effectively reduce data security risks in LLM-aided hardware design.
Although value-aligned language models (LMs) appear unbiased in explicit bias evaluations, they often exhibit stereotypes in implicit word association tasks, raising concerns about their fair usage. We investigate the mechanisms behind this discrepancy and find that alignment surprisingly amplifies implicit bias in model outputs. Specifically, we show that aligned LMs, unlike their unaligned counterparts, overlook racial concepts in early internal representations when the context is ambiguous. Not representing race likely fails to activate safety guardrails, leading to unintended biases. Inspired by this insight, we propose a new bias mitigation strategy that works by incentivizing the representation of racial concepts in the early model layers. In contrast to conventional mitigation methods of machine unlearning, our interventions find that steering the model to be more aware of racial concepts effectively mitigates implicit bias. Similar to race blindness in humans, ignoring racial nuances can inadvertently perpetuate subtle biases in LMs.
In recent years, Large Language Models (LLMs) have achieved remarkable advancements, drawing significant attention from the research community. Their capabilities are largely attributed to large-scale architectures, which require extensive training on massive datasets. However, such datasets often contain sensitive or copyrighted content sourced from the public internet, raising concerns about data privacy and ownership. Regulatory frameworks, such as the General Data Protection Regulation (GDPR), grant individuals the right to request the removal of such sensitive information. This has motivated the development of machine unlearning algorithms that aim to remove specific knowledge from models without the need for costly retraining. Despite these advancements, evaluating the efficacy of unlearning algorithms remains a challenge due to the inherent complexity and generative nature of LLMs. In this work, we introduce a comprehensive auditing framework for unlearning evaluation, comprising three benchmark datasets, six unlearning algorithms, and five prompt-based auditing methods. By using various auditing algorithms, we evaluate the effectiveness and robustness of different unlearning strategies. To explore alternatives beyond prompt-based auditing, we propose a novel technique that leverages intermediate activation perturbations, addressing the limitations of auditing methods that rely solely on model inputs and outputs.
Machine unlearning aims to remove the influence of specific training samples from a trained model without full retraining. While prior work has largely focused on privacy-motivated settings, we recast unlearning as a general-purpose tool for post-deployment model revision. Specifically, we focus on utilizing unlearning in clinical contexts where data shifts, device deprecation, and policy changes are common. To this end, we propose a bilevel optimization formulation of boundary-based unlearning that can be solved using iterative algorithms. We provide convergence guarantees when first-order algorithms are used to unlearn. Our method introduces tunable loss design for controlling the forgetting-retention tradeoff and supports novel model composition strategies that merge the strengths of distinct unlearning runs. Across benchmark and real-world clinical imaging datasets, our approach outperforms baselines on both forgetting and retention metrics, including scenarios involving imaging devices and anatomical outliers. This work establishes machine unlearning as a modular, practical alternative to retraining for real-world model maintenance in clinical applications.
We present a principled, per-instance approach to quantifying the difficulty of unlearning via fine-tuning. We begin by sharpening an analysis of noisy gradient descent for unlearning (Chien et al., 2024), obtaining a better utility-unlearning tradeoff by replacing worst-case privacy loss bounds with per-instance privacy losses (Thudi et al., 2024), each of which bounds the (Renyi) divergence to retraining without an individual data point. To demonstrate the practical applicability of our theory, we present empirical results showing that our theoretical predictions are born out both for Stochastic Gradient Langevin Dynamics (SGLD) as well as for standard fine-tuning without explicit noise. We further demonstrate that per-instance privacy losses correlate well with several existing data difficulty metrics, while also identifying harder groups of data points, and introduce novel evaluation methods based on loss barriers. All together, our findings provide a foundation for more efficient and adaptive unlearning strategies tailored to the unique properties of individual data points.
Machine unlearning, as a post-hoc processing technique, has gained widespread adoption in addressing challenges like bias mitigation and robustness enhancement, colloquially, machine unlearning for fairness and robustness. However, existing non-privacy unlearning-based solutions persist in using binary data removal framework designed for privacy-driven motivation, leading to significant information loss, a phenomenon known as over-unlearning. While over-unlearning has been largely described in many studies as primarily causing utility degradation, we investigate its fundamental causes and provide deeper insights in this work through counterfactual leave-one-out analysis. In this paper, we introduce a weighted influence function that assigns tailored weights to each sample by solving a convex quadratic programming problem analytically. Building on this, we propose a soft-weighted framework enabling fine-grained model adjustments to address the over-unlearning challenge. We demonstrate that the proposed soft-weighted scheme is versatile and can be seamlessly integrated into most existing unlearning algorithms. Extensive experiments show that in fairness- and robustness-driven tasks, the soft-weighted scheme significantly outperforms hard-weighted schemes in fairness/robustness metrics and alleviates the decline in utility metric, thereby enhancing machine unlearning algorithm as an effective correction solution.
The proliferation of large models has intensified the need for efficient data valuation methods to quantify the contribution of individual data providers. Traditional approaches, such as game-theory-based Shapley value and influence-function-based techniques, face prohibitive computational costs or require access to full data and model training details, making them hardly achieve partial data valuation. To address this, we propose Unlearning Shapley, a novel framework that leverages machine unlearning to estimate data values efficiently. By unlearning target data from a pretrained model and measuring performance shifts on a reachable test set, our method computes Shapley values via Monte Carlo sampling, avoiding retraining and eliminating dependence on full data. Crucially, Unlearning Shapley supports both full and partial data valuation, making it scalable for large models (e.g., LLMs) and practical for data markets. Experiments on benchmark datasets and large-scale text corpora demonstrate that our approach matches the accuracy of state-of-the-art methods while reducing computational overhead by orders of magnitude. Further analysis confirms a strong correlation between estimated values and the true impact of data subsets, validating its reliability in real-world scenarios. This work bridges the gap between data valuation theory and practical deployment, offering a scalable, privacy-compliant solution for modern AI ecosystems.
Unlearning in large language models (LLMs) is intended to remove the influence of specific data, yet current evaluations rely heavily on token-level metrics such as accuracy and perplexity. We show that these metrics can be misleading: models often appear to forget, but their original behavior can be rapidly restored with minimal fine-tuning, revealing that unlearning may obscure information rather than erase it. To diagnose this phenomenon, we introduce a representation-level evaluation framework using PCA-based similarity and shift, centered kernel alignment, and Fisher information. Applying this toolkit across six unlearning methods, three domains (text, code, math), and two open-source LLMs, we uncover a critical distinction between reversible and irreversible forgetting. In reversible cases, models suffer token-level collapse yet retain latent features; in irreversible cases, deeper representational damage occurs. We further provide a theoretical account linking shallow weight perturbations near output layers to misleading unlearning signals, and show that reversibility is modulated by task type and hyperparameters. Our findings reveal a fundamental gap in current evaluation practices and establish a new diagnostic foundation for trustworthy unlearning in LLMs. We provide a unified toolkit for analyzing LLM representation changes under unlearning and relearning: https://github.com/XiaoyuXU1/Representational_Analysis_Tools.git.
Large language models (LLMs) are increasingly deployed in real-world applications, raising concerns about the unauthorized use of copyrighted or sensitive data. Machine unlearning aims to remove such 'forget' data while preserving utility and information from the 'retain' set. However, existing evaluations typically assume that forget and retain sets are fully disjoint, overlooking realistic scenarios where they share overlapping content. For instance, a news article may need to be unlearned, even though the same event, such as an earthquake in Japan, is also described factually on Wikipedia. Effective unlearning should remove the specific phrasing of the news article while preserving publicly supported facts. In this paper, we introduce DUSK, a benchmark designed to evaluate unlearning methods under realistic data overlap. DUSK constructs document sets that describe the same factual content in different styles, with some shared information appearing across all sets and other content remaining unique to each. When one set is designated for unlearning, an ideal method should remove its unique content while preserving shared facts. We define seven evaluation metrics to assess whether unlearning methods can achieve this selective removal. Our evaluation of nine recent unlearning methods reveals a key limitation: while most can remove surface-level text, they often fail to erase deeper, context-specific knowledge without damaging shared content. We release DUSK as a public benchmark to support the development of more precise and reliable unlearning techniques for real-world applications.
Machine unlearning aims to selectively remove targeted knowledge from Large Language Models (LLMs), ensuring they forget specified content while retaining essential information. Existing unlearning metrics assess whether a model correctly answers retain queries and rejects forget queries, but they fail to capture real-world scenarios where forget queries rarely appear in isolation. In fact, forget and retain queries often coexist within the same prompt, making mixed-query evaluation crucial. We introduce SEPS, an evaluation framework that explicitly measures a model's ability to both forget and retain information within a single prompt. Through extensive experiments across three benchmarks, we identify two key failure modes in existing unlearning methods: (1) untargeted unlearning indiscriminately erases both forget and retain content once a forget query appears, and (2) targeted unlearning overfits to single-query scenarios, leading to catastrophic failures when handling multiple queries. To address these issues, we propose Mixed Prompt (MP) unlearning, a strategy that integrates both forget and retain queries into a unified training objective. Our approach significantly improves unlearning effectiveness, demonstrating robustness even in complex settings with up to eight mixed forget and retain queries in a single prompt.
Machine unlearning, the process of efficiently removing specific information from machine learning models, is a growing area of interest for responsible AI. However, few studies have explored the effectiveness of unlearning methods on complex tasks, particularly speech-related ones. This paper introduces UnSLU-BENCH, the first benchmark for machine unlearning in spoken language understanding (SLU), focusing on four datasets spanning four languages. We address the unlearning of data from specific speakers as a way to evaluate the quality of potential "right to be forgotten" requests. We assess eight unlearning techniques and propose a novel metric to simultaneously better capture their efficacy, utility, and efficiency. UnSLU-BENCH sets a foundation for unlearning in SLU and reveals significant differences in the effectiveness and computational feasibility of various techniques.
Recent advancements in deep models have highlighted the need for intelligent systems that combine continual learning (CL) for knowledge acquisition with machine unlearning (MU) for data removal, forming the Continual Learning-Unlearning (CLU) paradigm. While existing work treats CL and MU as separate processes, we reveal their intrinsic connection through a unified optimization framework based on Kullback-Leibler divergence minimization. This framework decomposes gradient updates for approximate CLU into four components: learning new knowledge, unlearning targeted data, preserving existing knowledge, and modulation via weight saliency. A critical challenge lies in balancing knowledge update and retention during sequential learning-unlearning cycles. To resolve this stability-plasticity dilemma, we introduce a remain-preserved manifold constraint to induce a remaining Hessian compensation for CLU iterations. A fast-slow weight adaptation mechanism is designed to efficiently approximate the second-order optimization direction, combined with adaptive weighting coefficients and a balanced weight saliency mask, proposing a unified implementation framework for gradient-based CLU. Furthermore, we pioneer task-agnostic CLU scenarios that support fine-grained unlearning at the cross-task category and random sample levels beyond the traditional task-aware setups. Experiments demonstrate that the proposed UG-CLU framework effectively coordinates incremental learning, precise unlearning, and knowledge stability across multiple datasets and model architectures, providing a theoretical foundation and methodological support for dynamic, compliant intelligent systems.
Large language models require iterative updates to address challenges such as knowledge conflicts and outdated information (e.g., incorrect, private, or illegal contents). Machine unlearning provides a systematic methodology for targeted knowledge removal from trained models, enabling elimination of sensitive information influences. However, mainstream fine-tuning-based unlearning methods often fail to balance unlearning efficacy and model ability, frequently resulting in catastrophic model collapse under extensive knowledge removal. Meanwhile, in-context unlearning, which relies solely on contextual prompting without modifying the model's intrinsic mechanisms, suffers from limited generalizability and struggles to achieve true unlearning. In this work, we introduce UniErase, a novel unlearning paradigm that employs learnable parametric suffix (unlearning token) to steer language models toward targeted forgetting behaviors. UniErase operates through two key phases: (I) an optimization stage that binds desired unlearning outputs to the model's autoregressive probability distribution via token optimization, followed by (II) a lightweight model editing phase that activates the learned token to probabilistically induce specified forgetting objective. Serving as a new research direction for token learning to induce unlearning target, UniErase achieves state-of-the-art (SOTA) performance across batch, sequential, and precise unlearning under fictitious and real-world knowledge settings. Remarkably, in terms of TOFU benchmark, UniErase, modifying only around 3.66% of the LLM parameters, outperforms previous forgetting SOTA baseline by around 4.01 times for model ability with even better unlearning efficacy. Similarly, UniErase, maintaining more ability, also surpasses previous retaining SOTA by 35.96% for unlearning efficacy, showing dual top-tier performances in current unlearing domain.
Image Generation models are a trending topic nowadays, with many people utilizing Artificial Intelligence models in order to generate images. There are many such models which, given a prompt of a text, will generate an image which depicts said prompt. There are many image generation models, such as Latent Diffusion Models, Denoising Diffusion Probabilistic Models, Generative Adversarial Networks and many more. When generating images, these models can generate sensitive image data, which can be threatening to privacy or may violate copyright laws of private entities. Machine unlearning aims at removing the influence of specific data subsets from the trained models and in the case of image generation models, remove the influence of a concept such that the model is unable to generate said images of the concept when prompted. Conventional retraining of the model can take upto days, hence fast algorithms are the need of the hour. In this paper we propose an algorithm that aims to remove the influence of concepts in diffusion models through updating the gradients of the final layers of the text encoders. Using a weighted loss function, we utilize backpropagation in order to update the weights of the final layers of the Text Encoder componet of the Stable Diffusion Model, removing influence of the concept from the text-image embedding space, such that when prompted, the result is an image not containing the concept. The weighted loss function makes use of Textual Inversion and Low-Rank Adaptation.We perform our experiments on Latent Diffusion Models, namely the Stable Diffusion v2 model, with an average concept unlearning runtime of 50 seconds using 4-5 images.
The variety of data in data lakes presents significant challenges for data analytics, as data scientists must simultaneously analyze multi-modal data, including structured, semi-structured, and unstructured data. While Large Language Models (LLMs) have demonstrated promising capabilities, they still remain inadequate for multi-modal data analytics in terms of accuracy, efficiency, and freshness. First, current natural language (NL) or SQL-like query languages may struggle to precisely and comprehensively capture users' analytical intent. Second, relying on a single unified LLM to process diverse data modalities often leads to substantial inference overhead. Third, data stored in data lakes may be incomplete or outdated, making it essential to integrate external open-domain knowledge to generate timely and relevant analytics results. In this paper, we envision a new multi-modal data analytics system. Specifically, we propose a novel architecture built upon the Model Context Protocol (MCP), an emerging paradigm that enables LLMs to collaborate with knowledgeable agents. First, we define a semantic operator hierarchy tailored for querying multi-modal data in data lakes and develop an AI-agent-powered NL2Operator translator to bridge user intent and analytical execution. Next, we introduce an MCP-based execution framework, in which each MCP server hosts specialized foundation models optimized for specific data modalities. This design enhances both accuracy and efficiency, while supporting high scalability through modular deployment. Finally, we propose a updating mechanism by harnessing the deep research and machine unlearning techniques to refresh the data lakes and LLM knowledges, with the goal of balancing the data freshness and inference efficiency.
Machine Unlearning (MU) aims to remove the information of specific training data from a trained model, ensuring compliance with privacy regulations and user requests. While one line of existing MU methods relies on linear parameter updates via task arithmetic, they suffer from weight entanglement. In this work, we propose a novel MU framework called Mode Connectivity Unlearning (MCU) that leverages mode connectivity to find an unlearning pathway in a nonlinear manner. To further enhance performance and efficiency, we introduce a parameter mask strategy that not only improves unlearning effectiveness but also reduces computational overhead. Moreover, we propose an adaptive adjustment strategy for our unlearning penalty coefficient to adaptively balance forgetting quality and predictive performance during training, eliminating the need for empirical hyperparameter tuning. Unlike traditional MU methods that identify only a single unlearning model, MCU uncovers a spectrum of unlearning models along the pathway. Overall, MCU serves as a plug-and-play framework that seamlessly integrates with any existing MU methods, consistently improving unlearning efficacy. Extensive experiments on the image classification task demonstrate that MCU achieves superior performance.
Lifelong learning algorithms enable models to incrementally acquire new knowledge without forgetting previously learned information. Contrarily, the field of machine unlearning focuses on explicitly forgetting certain previous knowledge from pretrained models when requested, in order to comply with data privacy regulations on the right-to-be-forgotten. Enabling efficient lifelong learning with the capability to selectively unlearn sensitive information from models presents a critical and largely unaddressed challenge with contradicting objectives. We address this problem from the perspective of simultaneously preventing catastrophic forgetting and allowing forward knowledge transfer during task-incremental learning, while ensuring exact task unlearning and minimizing memory requirements, based on a single neural network model to be adapted. Our proposed solution, privacy-aware lifelong learning (PALL), involves optimization of task-specific sparse subnetworks with parameter sharing within a single architecture. We additionally utilize an episodic memory rehearsal mechanism to facilitate exact unlearning without performance degradations. We empirically demonstrate the scalability of PALL across various architectures in image classification, and provide a state-of-the-art solution that uniquely integrates lifelong learning and privacy-aware unlearning mechanisms for responsible AI applications.
This paper introduces Ready2Unlearn, a learning-time optimization approach designed to facilitate future unlearning processes. Unlike the majority of existing unlearning efforts that focus on designing unlearning algorithms, which are typically implemented reactively when an unlearning request is made during the model deployment phase, Ready2Unlearn shifts the focus to the training phase, adopting a "forward-looking" perspective. Building upon well-established meta-learning principles, Ready2Unlearn proactively trains machine learning models with unlearning readiness, such that they are well prepared and can handle future unlearning requests in a more efficient and principled manner. Ready2Unlearn is model-agnostic and compatible with any gradient ascent-based machine unlearning algorithms. We evaluate the method on both vision and language tasks under various unlearning settings, including class-wise unlearning and random data unlearning. Experimental results show that by incorporating such preparedness at training time, Ready2Unlearn produces an unlearning-ready model state, which offers several key advantages when future unlearning is required, including reduced unlearning time, improved retention of overall model capability, and enhanced resistance to the inadvertent recovery of forgotten data. We hope this work could inspire future efforts to explore more proactive strategies for equipping machine learning models with built-in readiness towards more reliable and principled machine unlearning.
Our goal is to understand how post-training methods, such as fine-tuning, alignment, and unlearning, modify language model behavior and representations. We are particularly interested in the brittle nature of these modifications that makes them easy to bypass through prompt engineering or relearning. Recent results suggest that post-training induces shallow context-dependent ``circuits'' that suppress specific response patterns. This could be one explanation for the brittleness of post-training. To test this hypothesis, we design an unlearning algorithm, Layered Unlearning (LU), that creates distinct inhibitory mechanisms for a growing subset of the data. By unlearning the first $i$ folds while retaining the remaining $k - i$ at the $i$th of $k$ stages, LU limits the ability of relearning on a subset of data to recover the full dataset. We evaluate LU through a combination of synthetic and large language model (LLM) experiments. We find that LU improves robustness to adversarial relearning for several different unlearning methods. Our results contribute to the state-of-the-art of machine unlearning and provide insight into the effect of post-training updates.