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.

Oct 15, 2026

Not All Change Is Damage: Update-Matched Unlearning for Large Language Models

Unlearning aims to remove selected knowledge from large language models to mitigate privacy and safety risks while preserving useful capabilities. For models that continue to be fine-tuned after release, this goal is insufficient: they must also resist relearning the deleted knowledge while preserving plasticity, the ability to learn new tasks. Existing defenses train against simulated relearning while trying to preserve useful capabilities, but low relearning alone cannot distinguish selective resistance from a general loss of plasticity. Evaluating preservation after an update requires deciding what the updated model should remain close to. A pre-update reference penalizes useful changes induced by the update simply because they depart from earlier outputs. We therefore formulate the reference-timing hypothesis that, at comparable target suppression, an update-matched reference better preserves plasticity than a pre-update one. To test and address this hypothesis, we propose Update-Matched Unlearning (UMU), which applies the same simulated relearning update to the defended model and to an undefended reference initialized from the same unlearned model, and uses new-task learning to guide model selection. Extensive experiments on TOFU and FaithUn with Llama and Qwen models show that UMU improves both relearning resistance and plasticity across all three base unlearning methods, lowering harmful and benign relearning by 30.4 and 9.9 points on average while raising new-task accuracy by 3.5 points. When the reference does not receive the update, relearning remains similarly low but new-task accuracy falls below the base method, supporting the reference-timing hypothesis and showing that robust unlearning should prevent recovery selectively without suppressing learning itself.
Oct 14, 2026

Are We Really Measuring Forgetting? Pitfalls in Evaluating Machine Unlearning for Multimodal LLMs

As machine unlearning for multimodal large language models (MLLMs) rapidly advances, rigorous evaluation of its effectiveness becomes increasingly important. However, existing benchmarks largely inherit evaluation protocols from text-only unlearning and overlook the unique challenges of unlearning in multimodal settings. In this work, we identify three major pitfalls that may lead to misleading conclusions: the lack of heldout evaluation to distinguish genuine concept-wise forgetting from instance-wise overfitting, the reliance on synthetic, fine-tuned knowledge rather than real-world knowledge acquired during pre-training, and unfair method comparisons caused by applying the same training settings to different unlearning methods. To address these challenges, we introduce GEMMU (Generalizable Evaluation for Multimodal Machine Unlearning), a benchmark built on real-world knowledge and a principled evaluation protocol. Re-evaluating representative unlearning methods under GEMMU reveals substantial generalization gaps and challenges conclusions drawn from previous benchmarks. Our findings highlight the importance of rigorous evaluation for advancing multimodal machine unlearning and provide guidelines for future benchmark design.
Oct 14, 2026

RA2^2: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning

Large Language Model (LLM) unlearning is often evaluated primarily by target suppression and clean retain utility. These metrics can miss a local failure mode: a model may perform well on standard retain prompts, yet degrade on benign reasoning when prompts lie near the forgotten domain. This phenomenon is termed forget-adjacent utility loss. A fundamental question is: where should forget representations go after they leave the removed behavior? Successful unlearning depends not only on whether forget-conditioned representations depart from the harmful computation, but also on the direction in which they are redirected afterward. We propose RA2^2 (Retain-Anchored Attraction), a latent-space unlearning method that redirects forget-token states toward nearby retain-supported representations while preserving higher-layer behavior on retain data. On WMDP and MUSE, RA2^2 yields higher forget-adjacent utility than strong unlearning baselines at similar broad-utility levels. These results show that the migration direction of forget representations materially affects benign behavior near the forget boundary. Our code is available at https://github.com/ZacLing/retain_anchored_attraction.
Oct 13, 2026

Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents

Long-term memory has become a core component of large language model (LLM) agents. As agents accumulate personal information over long-term use, users increasingly ask them to delete sensitive or outdated facts. A memory system should honor such requests. It should remove exactly what was requested and keep the rest of its memory intact. However, existing memory benchmarks evaluate only memory writing, retrieval, and organization, so whether agents can forget at the user's explicit request remains under-evaluated. To address this gap, we propose Bemula, the first benchmark dedicated to memory unlearning. It comprises 50 multi-session dialogue instances, 135 forget requests of six types, and 1,742 test questions. Each dialogue has a control version without the requests, so that only systems that have stored the target can earn credit for forgetting. Across the paired versions, five test suites measure storage, removal of the requested information, preservation of unrelated memories, relearning of similar facts, and resistance to extraction attacks. On Bemula, we evaluate six mainstream memory systems under three backbone LLMs, together with the Full Context LLM on two of them. The results are negative. Across all evaluated systems and backbones, no system passes more than 1.5% of forget requests end to end, and most pass none at all. These systems either leave the requested information extractable under simple attacks or delete far more than requested. Memory unlearning therefore remains an open challenge for agent memory design. We release our data and code at https://github.com/Nboxff/bemula-benchmark.
Oct 13, 2026

Counterfactual Certification for Sequential Unlearning with Long-Run Performance Guarantees

Certified machine unlearning ensures the proximity between the unlearned model and a model retrained without the data to be forgotten. Extending this framework to sequential deletion requests, typically arriving as groups of variable size (e.g., all records of one user or of coordinated users), is challenging. For unlearning methods based on fine-tuning on the retain sets, this leads to either degrading performance or increasing computation as the number of unlearning requests grows. For independent successive requests, we instead certify each model release against a counterfactual unlearning trajectory in which the group being deleted never took part. With a fixed fine-tuning budget per deletion, we show that, for smooth strongly convex objectives, this approach keeps the performance loss bounded, uniformly in the number of requests. Experiments with multiclass logistic regression on FEMNIST show that the resulting algorithm needs fewer corrective steps than existing sequential methods and outperforms training-time differential privacy, particularly when group sizes are heterogeneous.
Oct 13, 2026

Can Agents Truly Forget? Explore Machine Unlearning for LLM Agents

Large language model (LLM) agents have shown strong capabilities in interactive problem solving, tool use, and long-horizon task execution. However, they may also acquire sensitive or private knowledge during training and expose it during deployment. Retraining a model from scratch to remove such knowledge is prohibitively costly, making machine unlearning a more practical approach. Machine unlearning aims to remove targeted undesirable knowledge from trained models without retraining from scratch while preserving general utility. When language models are deployed as agents, parameter-level unlearning becomes insufficient: forgotten information may still persist in memory artifacts or be reacquired via tool calls. In this paper, we formulate the problem of agent unlearning as removing private information from an LLM-based agent across three information channels: parametric knowledge, persistent memory, and tool-call acquisition. To study this problem, we introduce we introduce Agent Unlearning Benchmark (AUBench), a controlled benchmark that extends the fictitious-author setting of TOFU into an agent environment with persistent memory, an offline web snapshot, tool-accessible documents, and provenance-tracked interaction trajectories. By evaluating existing parameter-level and memory-level unlearning methods in this setting, AUBench reveals the gap between model-level forgetting and system-level agent unlearning, and provides a foundation for developing unlearning methods that operate across the full lifecycle of LLM agents.
Oct 10, 2026

CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation

Multimodal large language models (MLLMs) can reproduce sensitive, copyrighted, or unsafe information from their training data. Effective unlearning must remove target information while preserving non-target content, even within the same response. Existing methods typically apply uniform forgetting objectives to complete responses and rely on fixed, off-policy supervision, resulting in coarse token control and misalignment with the model's current behavior. We propose CUSE, a Counterfactual-guided Unlearning framework via on-policy Self-distillation for multimodal large language models. It first constructs counterfactual inputs by removing target-related evidence and uses the resulting changes in token probabilities to identify which tokens require stronger forgetting. It then distills token-level forgetting and retention targets on responses sampled from the current policy, with a frozen copy of the original model serving as the teacher model augmented with the corresponding forgetting- and retention-oriented privileged contexts. This design jointly determines what to forget and what to preserve. On MLLMU-Bench, CUSE reduces forget-set ROUGE-L by 33.6% while achieving 1.2% higher retain-set ROUGE-L than the strongest baseline.
Oct 10, 2026

Compositional Concepts Erasing: Disentangling Object-Style via Domain Manifold Unlearning

Diffusion models pose significant risks regarding the generation of illicit content and copyright violations. This has catalyzed the development of machine unlearning to erase harmful concepts or copyrighted styles from a model's generative repertoire without compromising its general performance. However, previous unlearning approaches on diffusion models have largely focused on either object-level or style-level removal and failed to address the challenge of object-style combination unlearning. At the same time, multiple unlearning requests often lead to catastrophic forgetting. To address these challenges, we propose Domain Manifold Unlearning (DMU), which uses an EMA-updated feature proxy extracted from intermediate diffusion features to represent the retained target-object direction. As a lightweight estimating representation of an object, DMU enables selective unlearning of domain-specific components in a specific object while preserving other semantic representations, thereby significantly enhancing robustness in multiple combination unlearning scenarios. Extensive experiments show that DMU significantly mitigates catastrophic forgetting, outperforming state-of-the-art methods of batch unlearning and sequential unlearning.
Oct 8, 2026

REDaCT: Collapse-Free Unlearning in Large Reasoning Models

Unlearning in large reasoning models (LRMs) requires removing forget-set information from both the reasoning trace and the final answer. Existing approaches achieve this objective at the cost of reasoning collapse, where the model fails to produce a coherent chain-of-thought (CoT) and does not properly terminate its reasoning process. To address this challenge, we propose REDaCT (REgenerate via Detection and Corrective Tuning), an inference-time unlearning framework for LRMs. REDaCT consists of two key components: (1) a binary leak detector that identifies sentences in the reasoning trace that leak forget-set information, and (2) an embedding optimization module that learns a corrective embedding offline, such that when injected at the first detected leak during inference, it guides subsequent reasoning towards sentences that do not leak forget-set information. Experimental results show that REDaCT completely avoids reasoning collapse, substantially improving reasoning preservation compared to state-of-the-art unlearning methods while maintaining perfect answer forgetting and near-perfect CoT forgetting. Our code is available at: https://github.com/jmaccoby/redact.
Oct 8, 2026

Not Every Change Is Necessary: Recoverable Drift in Large Language Model Unlearning

Machine unlearning in large language models aims to remove unwanted knowledge while preserving the model's remaining capabilities. Although existing methods use retention objectives or restrict where edits occur, achieving the desired forgetting level can still leave collateral changes that impair non-target behavior. Our recovery comparisons suggest that some of these changes can be reversed while preserving observed forgetting performance. In this work, we present Propose-Then-Project Unlearning (PTP-U), a framework that combines targeted forgetting with the recovery of non-target capabilities. PTP-U first applies local analytic edits to weaken target knowledge associations, then aligns non-target output distributions with those of the original model to recover capabilities while maintaining fixed forgetting constraints. Both stages serve a common goal: satisfying the forgetting requirements while preserving fluent generation and performance on non-target tasks. Across three benchmarks, PTP-U achieves the strongest forgetting-retention trade-off among evaluated methods, reaching 81.22%-91.03% forgetting while preserving 94.20% non-target utility on average. At matched forgetting, PTP-U consistently retains higher non-target utility.
Oct 8, 2026

Minimax Gaussian Mechanisms for Continual Machine Unlearning

Machine unlearning updates a trained model after records are deleted, aiming to match exact retraining without repeating the full training procedure. We develop Gaussian mechanisms for Newton updates under sequential deletion requests. Using Gaussian differential privacy (GDP) and its adaptive composition rule, we show that the full sequence of released models is statistically difficult to distinguish from matched exact retraining. To calibrate these mechanisms for empirical risk minimization, we derive upper bounds on the error of the Newton approximation relative to exact retraining and on how this error changes after each deletion batch. Independent Gaussian noise is calibrated using bounds on the full residual at each release, whereas Gaussian random walk noise uses smaller bounds on residual increments. These bounds yield allocations minimizing the worst-case maximum noise variance across releases under the resulting GDP certification constraints. With count-based bounds, the random walk asymptotically matches the worst-case variance of a single release at deletion cap MM, while independent noise incurs an additional factor of order MM. Set-based bounds can reduce the noise variances by using gradients and Hessians of the deleted records. For singleton deletion, we further show that count-based independent noise, count-based random walk noise, and set-based independent noise are minimax among fixed Gaussian covariances under their respective residual or increment bounds. With set-based bounds, allowing variances to adapt to deleted records can improve on every fixed covariance by a factor of order (log⁡M)2(\log M)^2 on some data sequences. The residual and noise bounds also yield parameter and predictive consistency relative to exact retraining, uniformly over deletion policies. Simulations and a credit default data analysis evaluate bounds, noise variances, and estimation errors.
Oct 7, 2026

Why Forget-Only Unlearning Needs Memorization

Machine unlearning asks for a deletion algorithm whose output is close to retraining from scratch without the selected forget examples. In this work, we study forget-only unlearning, where the deletion algorithm receives only the trained model and the examples to forget, with no retained data or extra training information. We ask whether forget-only unlearning is always possible. We first show that this depends on the learning method: different datasets can produce the same trained model but require very different outputs after the same examples are removed. Using this observation, we derive lower bounds on how accurately unlearning can match retraining and instantiate them for several standard learning algorithms. We then ask what must be true when forget-only unlearning succeeds. To this end, we derive lower bounds on what an algorithm must memorize about the training data to handle arbitrary deletion requests. For simple threshold learners, the required information can be as large as the entire dataset, even though ordinary training keeps only one boundary point. Overall, our results show that information discarded during ordinary learning may be needed later for deletion, so models designed for forget-only unlearning may need to retain more information than standard training does.
Oct 6, 2026

Removing Information Content Does Not Certify Tamper Resistance in Open-Weight Models

Does removing harmful information make open-weight models resistant to fine-tuning attacks? We show that mutual information at release alone cannot universally certify slow recovery. Function-preserving reparameterizations leave information unchanged while altering gradient-descent geometry, so an invariant certificate is bounded by the fastest reachable parameterization. We apply this principle to weight--data mutual information under training-data filtering and label--representation mutual information under capability removal. Training order can change recovery time at fixed weight--data information, while exact representation-level independence can preserve the entire parameter Jacobian. An explicit construction has both information quantities equal to zero and recovers in one gradient step. Controlled experiments illustrate order-dependent recovery and parameterization-dependent attack speed. These results identify the missing requirement for certification: constraints on attack dynamics beyond mutual information at release.
Oct 6, 2026

How Learning Governs Unlearning across the Memorization-Generalization Spectrum

While unlearning seeks to negate undesired capabilities acquired through learning, little research has examined how the way models learn shapes their subsequent unlearning. In this paper, we investigate this connection from the perspectives of memorization and generalization, the two most representative yet competing strategies that models employ during training. We first classify memorization- and generalization-heavy models using grokking in modular addition and compare their responses to unlearning, showing that the latter suffer greater retain damage, i.e., a larger performance drop on the retain set. Furthermore, we conduct a finer-grained analysis by introducing bucketed modular addition, in which the respective contributions of the two strategies can be explicitly controlled across the memorization-generalization spectrum. In this setup, we reaffirm that the same trend persists and is nearly monotonic. We further demonstrate that this relationship also holds in LLM unlearning across verbatim and factual recall settings. Finally, we provide two practical insights for developing better unlearning methods, highlighting the importance of accounting for learning dynamics in unlearning.
Oct 5, 2026

Exact Unlearning via Quantized Sufficient Statistics

Exact unlearning requires a deployed predictor to match one rebuilt without the information named by a deletion request. Existing general-purpose exact methods localize retraining through disjoint shards, but every request still invalidates a model, and smaller shards reduce the data available to each constituent predictor. We introduce Quantized Sufficient Statistics (QSS), which separates a small frozen schema from mutable, sum-decomposable content. The schema learns global structure; the content stores local prediction corrections as additive statistics indexed by quantized regions. Deleting content is therefore exact subtraction rather than optimization. We distinguish two guarantees: QSS-L exactly removes a label while retaining the unlabelled input, whereas QSS-E exactly removes both input and label by learning the schema without deletable examples. A deletion takes the arithmetic fast path with probability 1−ρ1-ρ and triggers a full rebuild with probability ρρ; all reported expected latencies include both events. Across 15 vision, text, and tabular datasets at ρ=0.5%ρ=0.5\%, QSS-L is within 2 percentage points of SISA on 11 tasks and provides 4--483×\times lower expected deletion latency on the low-class-count tasks where a compact schema is effective. QSS-E quantifies the additional accuracy cost of removing every trace of an input.
Oct 4, 2026

Your Unlearning Gives You Away: Identifying Erased Concepts in Diffusion Models

Existing attacks on unlearned diffusion models assume that the erased concepts are known in advance and focus on recovering them. In practice, however, model providers may not disclose which concepts have been removed, and even with access to the original base model, an adversary may still lack a clear target to attack. In this paper, we aim to answer the following critical but overlooked questions: which concepts have been erased from the model, and how many have been erased in total? To this end, we present Tracer, a framework that rapidly and accurately identifies erased concepts and estimates their number. Tracer efficiently identifies erased concepts without generating and classifying images. By combining lightweight spectral analysis of weight footprints, it enables efficient search over large candidate vocabularies. To distinguish multiple erased concepts, we introduce a footprint coverage objective that guides sequential discovery. Tracer estimates the number of erased concepts by detecting a sharp decline in candidate confidence as the selected concepts account for the erasure footprint, without requiring labeled examples for calibration. The framework requires only lightweight linear algebra and limited forward probes, with no prior knowledge of the unlearning algorithm. Experiments across text-to-image and text-to-video backbones and diverse unlearning methods demonstrate that Tracer identifies erased concepts and estimates their number in seconds, achieving 150 to 137,000 times and 133 to 20,000 times speedups over MIA and brute-force search on image and video models, respectively, with substantially higher identification accuracy.
Oct 3, 2026

UnAct: Gradient-Free Unlearning via Targeted Activation Intervention

Machine unlearning seeks to remove the influence of designated training data from a trained model without retraining from scratch. Retrain-free methods such as Selective Synaptic Dampening (SSD) and its label-free variant LFSSD avoid full retraining but still require backpropagation and parameter importance computed over the entire dataset. We ask: what happens when a deletion request arrives with only a few images of the class to be forgotten? To answer this question, we introduce UnAct, a gradient-free class-unlearning method that needs only forward passes over the forget images. UnAct scores late-layer units by their responses, attenuates the most responsive connections, and repeats this for up to 20 rounds using no gradients, no labels, and no retained data. On ResNet-18 trained with CIFAR-10, CIFAR-20, and CIFAR-100, UnAct is competitive with SSD and LFSSD when forgetting entire classes and, unlike them, never collapses the network when forget data is scarce. On ResNet-18, across all tested sizes, UnAct's retain accuracy stays within 2.5 points of retraining, while SSD and LFSSD, at their full-class operating points, lose up to 86 points on some classes. With five forget images on CIFAR-10, UnAct's distance to retraining is 0.21 points, against 67 for LFSSD and 90 for SSD, and re-selecting SSD's threshold at each size with an oracle does not close the gap. In preliminary transfer to ViT-B/16, UnAct's distance to retraining is 11.5 against 33.7 for SSD, and a request is 19x faster than SSD when SSD computes its importance at request time. The code is available at https://github.com/abdulmuizz0903/UnAct
Oct 3, 2026

Modeling Deletion Requests in Machine Unlearning

Machine unlearning is seen as a promising approach to enable users to exercise the "right to erasure" in the context of AI models. We ask how users might influence the behavior of models when exercising this right. We define two types of behaviors that users might adopt when requesting the deletion of their data: adaptivity and collectivity. Drawing connections between the goals of users in this context and results in stochastic optimization, we demonstrate theoretical gaps between the potential effects of groups of users who do and do not display these behaviors. We then show how techniques from data valuation might be used to design deletion requesters that can significantly alter model behavior in realistic settings. In experiments on computer vision tasks, we demonstrate the differential effects of different models of user behavior and attempt to isolate the impacts of adaptivity and collectivity.
Oct 2, 2026

FADE: Frame-Aware Diffusion-Transformer-based Multi-Concept Erasure for Video Unlearning

Text-to-video (T2V) diffusion models can reproduce copyrighted, violent, or explicit content, which motivates concept erasure: removing designated concepts from a pretrained model while preserving its behavior on everything else. Existing T2V erasure methods leave two problems open. Their frame-agnostic suppression can leave isolated frames in which an erased concept resurfaces, a frame-reactivation gap that clip-level averages obscure; and they are usually evaluated with one target concept or category at a time. We propose Frame-Aware Diffusion Erasure (FADE), a multi-concept video unlearning framework. FADE first applies a joint closed-form key/value edit that suppresses all target concepts, then trains per-concept frame-aware low-rank adapters whose strength is gated by the frame index and the denoising timestep to remove residual per-frame leakage. Each adapter is trained with the other targets' prompts as hard negatives, which keeps the concept-specific components of different adapters well separated, and a similarity-based soft router combines the adapters according to the prompt. With 16 concepts (objects, artistic styles, and nudity) erased from a single Wan2.1-T2V-1.3B backbone, FADE reduces the residual accuracy on the object benchmark to 4.9%, against 15.5% for the strongest of eight baselines, while keeping the VBench average within 0.9% of the unedited model. The ranking is unchanged under a VLM judge and a blinded human study, and the advantage over the strongest baseline carries over to prompts that combine several erased concepts, to 30 simultaneously erased celebrity identities, and to Wan2.1-T2V-14B, CogVideoX-2B, and HunyuanVideo-1.5.
Oct 2, 2026

Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation

Mechanistic edits (ablations, weight edits, activation steering) are the standard tools for unlearning a harmful capability from a neural network while preserving useful ones. Current approaches validate their effects only by testing, which can never cover an entire continuous region of inputs. Prior work at the interpretability-verification boundary certifies descriptions of a model: what a circuit computes, or whether it faithfully explains the whole. We instead certify the behavioral effect of an edit: that disabling a circuit removes one skill and provably preserves another, for every input in a region; a feature non-interference guarantee in the information-flow-security sense. We demonstrate such certified edits from toy ReLU networks up to a standard softmax + LayerNorm transformer, proving removal and preservation over continuous embedding-space regions and reaching roughly 9x the input-perturbation dimension an exact solver can handle by switching to sound bound propagation. Furthermore, we prove that no finite deterministic black-box test can certify removal, exhibiting an edit that passes exhaustive testing yet provably fails on a survivor pocket that can be made arbitrarily small. Guarantees hold on small, standard-architecture networks and, like any removal claim, presuppose that the target skill admits a decidable specification, a property which real-world harms may not have.
Oct 2, 2026

On Unlearning for Time-series Forecasting

Time-series forecasting is widely used in sensitive domains. Models in these settings are often trained on longitudinal user- or entity-level records, which may later require removal because they contain sensitive or proprietary information or have been corrupted by sensor failures. To address such deletion requests without costly retraining, machine unlearning has been widely studied as a practical mechanism for privacy protection and data governance. However, the application of machine unlearning to time series prediction has not yet been well realized; this is mainly due to the following unique challenges: Gradient-based unlearning can be unstable because a deleted observation participates in multiple causally connected forecasting windows, causing parameter updates to propagate beyond the requested interval and degrade retained forecasting utility. Label-guided updating offers a more controlled alternative, but continuous and context-dependent forecasts lack a suitable replacement target, while the exact-retrained output is unavailable during unlearning. Moreover, the remaining support for a deleted temporal pattern is highly non-uniform. Some affected windows retain structurally similar counterparts in the retained data, whereas others become underrepresented or isolated. We present RDTU, a Residual Diffusion framework for time-series unlearning. RDTU first uses a retained-set neural tangent kernel predictor to obtain a deletion-compatible base forecast. Then it quantifies the global and local structural support of each affected window using the volume contribution of the retained-reference data. Then a diffusion model generates a residual correction that estimates the counterfactual forecast, yielding a pseudo-label field that guides a lightweight model update. Experiments show that RDTU consistently produces unlearned models that most closely match exact retraining.
Oct 1, 2026

SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning

The ability of vision-language models (VLMs) to associate visual identities with biographical information creates a need for selective unlearning of personally identifiable information (PII) while preserving permitted knowledge about the same individual. This setting is challenging because both sensitive and retained information can share the same visual inputs and intermediate representations. We introduce SIEVE, a simple and effective framework for selective VLM unlearning. SIEVE directly regularizes attention-value representations while also controlling model outputs. SIEVE suppresses attention values for forget examples toward a constant zero, while preserving retain-example representations by matching them to a frozen reference model. These objectives are combined with sequence-level forget and retain supervision, enabling targeted forgetting without largely affecting retained knowledge. Extensive experiments show that SIEVE achieves state-of-the-art performance on unlearning with multiple model-modality settings, while maintaining competitive retained utility. Ablation studies further show that value suppression and negative cross-entropy contribute complementary forgetting signals, while reference-based value matching substantially reduces utility degradation. These results demonstrate that attention values provide an effective intervention point for selective multimodal unlearning when sensitive and retained knowledge are closely related.
Oct 1, 2026

Repurposing Obsolete Representations for Post-Deployment Adaptation

Deep neural networks are increasingly deployed in long-lived systems, where task requirements may change after training. In such settings, part of the original output space may become obsolete: a class, prediction region, or learned behaviour may no longer be valid. Existing approaches either leave the obsolete behaviour intact or require fine-tuning, which can be expensive. We propose Deep Repurposing (DR), a post-hoc framework for adapting models under task obsolescence. DR estimates the latent geometry of obsolete and retained regions, removes obsolete-supporting components, and reallocates retained-compatible evidence through an analytic repair map without gradient updates. This yields repaired predictions and representations in which obsolete regions no longer act as valid outputs, while useful obsolete structure can support the retained task. Across multiple task settings, DR removes obsolete behaviour while preserving retained utility. More importantly, across classification benchmarks, DR matches or exceeds competing unlearning and editing baselines in retained accuracy, eliminates obsolete predictions, and adapts up to 60×60\times faster than competing unlearning methods.
Oct 1, 2026

When Is Deletion Ordering Tractable? From Update Dynamics to Permutation Structure

Given a fixed set of pending deletion requests, retraining from scratch after each request is prohibitive, so a prescribed request-wise policy processes them sequentially. The resulting terminal model can depend on their order. Rather than prescribing an ordering rule, we study the permutation objective induced by the fixed policy and ask when it admits simpler structure. We identify two independent reductions: position additivity represents the objective by request--position costs, reducing optimization to assignment and, with a shared positional profile, sorting; suffix localization removes dependence on the distant prefix while retaining interactions among the surviving requests. Under shared affine updates, we characterize the quadratic interactions that obstruct additivity, prove the reductions' independence, and show that suffix-conditioned assignment improves the approximation rate from O(p^L) toO(p^(2L)). Experiments recover both structures in executed objectives. A controlled damped-Newton sweep shows that stronger contraction shifts the objective toward shorter, more suffix-specific dependence, while two full-network policies exhibit distinct positional and within-suffix structure. Structures identified from compact execution sets also predict unseen orders. These results frame deletion ordering as identifying the computational structure induced by the executed updates.
Oct 1, 2026

From Mathematical to Executable Certificates for Machine Unlearning

Machine unlearning is needed when data must be removed because of deletion requests, outdated records, or data-quality concerns, while retraining from scratch can be costly. Certified machine unlearning methods provide mathematical guarantees, while deployed systems release concrete finite-precision artifacts produced by software. To bridge the gap between mathematical guarantees and practical deployment, we introduce Executable Release Certification (ExecCert), a release-time layer that certifies the candidate artifact considered for release. ExecCert either closes a method's native certificate for the executed candidate or applies Retraining-Reference Release Verification (RRV) to certify fidelity to current retain-set retraining. Sequential deletion makes the latter nontrivial because the exact retain-set reference and the stored numerical state evolve separately. For frozen representations with a mutable ridge head, we develop an incremental realization of RRV that maintains certified evidence across deletion requests rather than reconstructing it at each release. On four published unlearning implementations, ExecCert preserves valid certificates, changes release decisions, tightens conservative bounds, and identifies the retraining-reference fidelity supported by concrete outputs. In sequential-service experiments, RRV eliminates false releases caused by stored-equation verification while closely tracking realized error, and incremental certification remains cheaper than both fresh and maintained verified-factor alternatives once release checks become sufficiently frequent.
Sep 30, 2026

State-Space Unlearning for Non-Stationary Bias in Land Surface Forecasting

Operational land surface forecasting systems built on Mamba-family Structured State Space Models absorb non-stationary confounding events (unrecorded irrigation booms, dam-operation shifts, sensor recalibrations) into their state-transition matrices, silently biasing NDVI, LST, and crop phenology predictions long after the physical cause ends. This paper introduces SSU-LSF (State-Space Unlearning for Land Surface Forecasting), the first machine-unlearning framework purpose-built for geoscientific Mamba-based SSMs. We develop EKFac influence functions specialized to the Mamba state matrices via a closed-form matrix-exponential gradient, use spectral-radius-weighted elbow thresholding to localize a temporal confounding footprint ΦΦ, and apply Hessian-free projected gradient ascent within a KL-divergence trust region augmented by spatial total-variation (TV) regularization. Proposition 1 establishes that residual confounding is bounded by O((1−ρ(Aˉ)Tc)/((1−ρ(Aˉ))μ))\mathcal{O}\big((1-ρ(\bar{A})^{T_c})/((1-ρ(\bar{A}))μ)\big), which grows with the window length TcT_c. Across three heterogeneous benchmarks and eleven baselines, SSU-LSF achieves confounding reduction rates of 0.7730.773 (CropHarvest), 0.8210.821 (NDVI-LST), and 0.8590.859 (ERA5), with worst-case clean-domain RMSE degradation of 4.2%4.2\% on ERA5, converging in 3--5 epochs at 8.4×8.4\times lower GPU-cost per unlearning request than full retraining. Code: https://github.com/Anidipta/SSU-LSF
Sep 30, 2026

Linguistic Loopholes in LLM Unlearning: From a 174-Language Benchmark to Coverage-Aware Unlearning

Unlearning a fact in one language does not guarantee its removal in others as changing the query or even the requested answer language can reopen seemingly forgotten knowledge -- a cross-lingual loophole. The most straightforward solution to this challenge -- unlearning in all languages -- is neither scalable nor desirable as it amplifies damage to unrelated model capabilities. We introduce the task of language budgeted multilingual unlearning where the goal is to select a subset of languages that maximizes cross-lingual erasure. To study this task we introduce the Cross-Lingual Unlearning Tensor, an unlearning benchmark that spans 174 language--script pairs and 25 atomic paraphrase types to examine when forgetting generalizes across linguistic expressions of the same knowledge. We further propose COVER, which selects source languages to maximize predicted COVERage of languages receiving no forget supervision, enabling unlearning on a language budget. Surprisingly, we find naively selecting strong individual sources does not reliably compose into strong source sets motivating our development of COVER. At deployment COVER only requires benign calibration data and access to the frozen model. Across three model families and two disjoint forget sets, COVER reduces mean held-out residual access by 7.8--27.3% relative to uniform source selection. We find these gains extend beyond synthetic benchmarks to real news documents in low-resource language settings using human translated data from the Low Resource Languages for Emergent Incidents (LORELEI) corpus.
Sep 30, 2026

LLM Persona Unlearning

Pre-training equips large language models (LLMs) with a broad repertoire of behavioral patterns associated with roles, styles, values, and goals. Post-training teaches conditional enactment and makes a helpful Assistant the default, but it does not erase alternative modes from the weights; explicit prompts can therefore elicit personas that repeatedly shape judgment, language, and action. In open-weight settings, runtime controls can be removed, motivating persona unlearning: a weight-level edit that makes a designated persona difficult to elicit and enact on unseen contexts. We introduce PersonaUnlearnBench, a model-specific paired benchmark spanning six LLMs from three families and five personas, with aligned forget/retain sets, held-out instruction paraphrases, and four-axis evaluation. The benchmark shows that standard unlearning methods cannot reliably erase the target persona without sacrificing meaningful generation or general utility. We therefore propose PaCE, which compares target and desirable responses to the same questions to locate an internal behavior direction, then trains target-prompt states away from the target mode and toward the matched desirable response. Experiments show that PaCE consistently suppresses target personas with high response quality and useful counterpart behavior, at moderate utility cost. These results establish persona unlearning as a distinct behavior-level editing problem and a practical route toward persistent control of latent LLM response policies.
Sep 30, 2026

FOMO: Forget the Concept, Don't Miss Out on the Scene in Selective Video Unlearning

The rapid advancement of generative video models has enabled the synthesis of increasingly realistic and temporally coherent videos, while also raising concerns about the generation of harmful content. The reliance on large-scale web datasets during training inevitably exposes these models to undesirable material, making concept unlearning an essential mitigation. Existing methods mainly target static visual concepts, such as objects, identities, or unsafe appearance, largely overlooking motion unlearning. Furthermore, these approaches often pay little attention to preserving the surrounding scene. As a result, successful concept removal may unintentionally alter the background, composition, or overall video dynamics. We argue that effective unlearning should ideally change only what is targeted, while minimizing unnecessary changes to the remaining scene. In this work, we introduce FOMO, to the best of our knowledge the first training-based selective video unlearning method that directly treats preservation of the original scene as a priority. We formulate unlearning around two complementary objectives: what to change and what to preserve. Our method localizes concept-related representations and modifies them, while the preservation mechanism maintains non-target scene information without requiring auxiliary data. Beyond simply erasing unwanted concepts, FOMO explicitly redirects the generation toward a specified safe alternative. We further extend this formulation to motion unlearning, where the concept is defined by temporal behavior rather than a fixed spatial region. Our solution achieves effective unlearning across unsafe content, object, and motion concepts, while achieving the best trade-off between concept removal and scene preservation. Code: https://github.com/gmum/FOMO Project Page https://gmum.github.io/FOMO
Sep 30, 2026

Faithful Dual-constrained Erasure for Robust LLM Safety Alignment

Machine unlearning has emerged as a crucial mechanism for removing hazardous knowledge and enforcing safety alignment in Large Language Models (LLMs). However, recent studies reveal a persistent security risk: unlearned models remain highly vulnerable to retraining attacks, where suppressed malicious behaviors rapidly resurface after benign fine-tuning. In this work, we investigate the optimization dynamics of unlearning and identify that this vulnerability stems from shallow alignment. Rather than effectively erasing target knowledge, models often exploit a shortcut by activating previously dormant parameters to act as spurious suppressors, forming a fragile inhibitory shell over intact malicious representations. To address this issue and enforce authentic memory deletion, we propose FDCU, a novel dual-constrained subspace projection framework. FDCU restricts parameter updates through a highly scalable, element-wise dual-masking rule: it preserves general knowledge manifolds via Fisher Information and strictly prohibits the abnormal activation of spurious suppressors via the Principle of Minimal Functional Intervention (PMFI). By reliably blocking the model's ability to superficially hide knowledge, FDCU promotes the authentic dismantling of target representations. Extensive experiments across specific knowledge erasure and safe output control tasks demonstrate that FDCU achieves state-of-the-art robustness against retraining attacks while maintaining near-lossless general utility, ensuring durable safety for LLMs.