Concept Erasure

Machine unlearning has reached a critical bottleneck. As traditional weight-space interventions focus primarily on erasing targeted concepts, they often fail to prevent the unintended suppression of other significant representations. This leads to substantial collateral damage, with essential knowledge being forgotten, because these methods lack formal mathematical guarantees for the preservation of neutral concepts. To avoid degradation, they are frequently forced into conservative updates. We propose BARRIER (Bounded Activation Regions for Robust Information Erasure), a paradigm-shifting framework that shifts the locus of intervention from static model weights to the dynamic geometry of hidden-layer activations. Unlike existing methods, BARRIER employs Interval Arithmetic (IA) on SVD-based projections of the activation space to encapsulate the specific target region within a bounding hypercube. By driving unlearning updates exclusively within this forget interval and mathematically bounding the model response on the complement, we ensure rigorous protection of the retain distribution. This geometric construction transforms the preservation of knowledge from an empirical heuristic into a formal optimization target with a probabilistic tail bound on functional drift. Crucially, this stability permits highly aggressive unlearning updates within the forget region. Empirical evaluations demonstrate that BARRIER matches state-of-the-art trade-offs across classifiers and diffusion models, maximizing targeted concept erasure while safeguarding the integrity of all other representations. Our code is available at https://github.com/OneAndZero24/BARRIER.

Standard unlearning evaluations measure behavioral suppression in full precision, immediately after training, despite every deployed language model being quantized first. Recent work has shown that 4-bit post-training quantization can reverse machine unlearning; we show this is not a tuning artefact but a systematic dual failure: gradient-based methods that achieve meaningful forgetting lose it under compression, while methods that survive quantization barely change the model. Both failures trace to the same root cause: across all baselines, per-parameter updates lie 47-828x below the NF4 quantization bin width; updates diffused across billions of parameters cannot clear quantization bin boundaries, a consequence we formalize as a sparsity-permanence tradeoff. We present MANSU (Mechanistic-Aligned Null-Space Unlearning), which resolves both modes by combining causal circuit attribution to isolate the minimal forget-set subgraph, circuit-restricted null-space projection with a diagonal-Fisher retain bound, and a per-parameter magnitude floor guaranteeing quantization survival by construction. We additionally introduce Circuit Attribution Divergence (CAD), a mechanistic verification metric distinguishing structural erasure from behavioral suppression, a distinction existing metrics cannot make. Across multiple model families and hazard benchmarks, MANSU is the first method to jointly satisfy all four properties with margin on each (meaningful forgetting, retain preservation, non-positive PTQ gap, and structural erasure), while gradient-based baselines recover up to +0.05 accuracy under compression.

Erasing specific concepts from text-to-image diffusion models is essential for avoiding the generation of copyrighted and explicit content. Closed-form concept erasure methods offer a fast alternative to backpropagation-based techniques, but they become less effective when scaling from smaller models such as Stable Diffusion 1.5 to larger models like Stable Diffusion XL. To maintain erasure effectiveness in these larger-scale architectures, we propose SParse cross-Attention-based Concept Erasure (SPACE). SPACE iteratively modifies the cross-attention parameters of a model with a closed-form update that jointly induces sparsity and erases target concepts. By concentrating the concept mapping to a lower-dimensional subspace, SPACE achieves superior erasure efficacy compared to dense baselines. Extensive experimental results show improvements in erasure effectiveness and robustness against adversarial prompts. Furthermore, SPACE achieves 80%-90% cross-attention sparsity, reducing the storage requirements for saving the modified parameters by 70%, demonstrating its memory efficiency.

Recent advancements in Vision-Language Models (VLMs) enable large language models (LLMs) to process high-resolution images, significantly improving real-world multimodal understanding. However, this capability introduces a large number of vision tokens, resulting in substantial computational overhead. To mitigate this issue, various vision token pruning methods have been proposed. Nevertheless, existing approaches predominantly rely on learned semantic features within the model to capture visual redundancy. Moreover, they lack adaptive mechanisms to adjust pruning strategies according to the complexity of the input image. In this paper, we propose ERASE, a two-stage vision token pruning framework that identifies and retains salient tokens through pruning strategies adaptive to image complexity. Experiment results demonstrate that ERASE significantly reduces vision tokens while preserving accuracy. For Qwen2.5-VL-7B, at a token pruning ratio of 85%, ERASE retains 89.46% of the original model accuracy, whereas the best prior method retains only 78.1%. Our code is available at https://github.com/Tuna-Luna/ERASE.

Large Vision-Language Models (LVLMs), trained on web-scale data, risk memorizing and regenerating copyrighted visual content such as characters and logos, creating significant challenges. Machine unlearning offers a path to mitigate these risks by removing specific content post-training, but evaluating its effectiveness, especially in the complex multimodal setting of LVLMs, remains an open problem. Current evaluation methods often lack robustness or fail to capture the nuances of cross-modal concept erasure. To address this critical gap, we introduce the CoVUBench benchmark, the first framework specifically designed for evaluating copyright content unlearning in LVLMs. CoVUBench utilizes procedurally generated, legally safe synthetic data coupled with systematic visual variations spanning compositional changes and diverse domain manifestations to ensure realistic and robust evaluation of unlearning generalization. Our comprehensive multimodal evaluation protocol assesses both forgetting efficacy from the copyright holder perspective and the preservation of general model utility from the deployer viewpoint. By rigorously measuring this crucial trade-off, CoVUBench provides a standardized tool to advance the development of responsible and effective unlearning methods for LVLMs.

Understanding how neural models represent human-interpretable concepts is challenging. Prior work has explored linear concept subspaces from diverse perspectives, such as probing and concept erasure. We introduce a unified framework to study these subspaces along two axes: \textit{containment}, which tests if a concept is fully represented in a subspace but not outside it, and \textit{disentanglement}, which tests for isolation from other concepts. In experiments on both text and speech models, we first highlight that concept subspaces may not be uniquely determined, and discuss the implications for concept subspace analysis. Then, we compare properties of concept subspaces estimated using five estimators, proposed in different communities. We find that (1) the choice of estimator impacts the containment and disentanglement properties; (2) the state-of-the-art concept erasure method, LEACE, performs well on both testing axes, but still struggles to generalize to unseen data; and (3) in HuBERT speech representations, phone information is both contained and disentangled from speaker information, while speaker information is hard to contain in a compact subspace, despite being disentangled from phones.

Deepfake technologies have rapidly advanced with modern generative AI, and face swapping in particular poses serious threats to privacy and digital security. Existing proactive defenses mostly rely on pixel-level perturbations, which are ineffective against contemporary swapping models that extract robust high-level identity embeddings. We propose ID-Eraser, a feature-space proactive defense that removes identifiable facial information to prevent malicious face swapping. By injecting learnable perturbations into identity embeddings and reconstructing natural-looking protection images through a Face Revive Generator (FRG), ID-Eraser produces visually realistic results for humans while rendering the protected identities unusable for Deepfake models. Experiments show that ID-Eraser substantially disrupts identity recognition across diverse face recognition and swapping systems under strict black-box settings, achieving the lowest Top-1 accuracy (0.30) with the best FID (1.64) and LPIPS (0.020). Compared with swaps generated from clean inputs, the identity similarity of protected swaps drops sharply to an average of 0.504 across five representative face swapping models. ID-Eraser further demonstrates strong cross-dataset generalization, robustness to common distortions, and practical effectiveness on commercial APIs, reducing Tencent API similarity from 0.76 to 0.36.

We develop a thermodynamic theory of algorithmic catalysis within the watts per intelligence framework, identifying reusable computational structures that reduce irreversible operations for a task class while satisfying bounded restoration and structural selectivity constraints. We prove that any class specific speed-up is upper-bounded by the algorithmic mutual information between the substrate and the class descriptor, and that encoding this information incurs a minimum thermodynamic cost via Landauer erasure. Combining these results yields a coupling theorem that lower-bounds the deployment horizon required for an algorithmic catalyst to be energetically favourable. The framework is illustrated on an affine SAT class and situates contemporary learned systems within an information thermodynamic constraint on intelligent computation.

Steering intermediate representations has emerged as a powerful strategy for controlling generative models, particularly in post-deployment alignment and safety settings. However, despite its empirical success, it currently lacks a comprehensive theoretical framework. In this paper, we bridge this gap by formalizing the theory of concept steering. First, we establish a link between steering and affine concept erasure, proving that the standard approach for removing unwanted behaviors is a special case of LEACE (a closed-form method for affine erasure). Next, we formulate a principled theoretical framework for concept switching, LEACE-Switch, and characterize the assumptions under which it provides an optimal affine solution. Building on this analysis, we then introduce MidSteer (Minimal Disturbance concept Steering), a more general affine framework for concept manipulation that relaxes these assumptions and enables directed, minimal-disturbance transformations. We demonstrate that MidSteer performs favorably across a range of tasks, modalities, and architectures, including vision diffusion models and large language models.

Text-to-image generative models have achieved impressive fidelity and diversity, but can inadvertently produce unsafe or undesirable content due to implicit biases embedded in large-scale training datasets. Existing concept erasure methods, whether text-only or image-assisted, face trade-offs: textual approaches often fail to fully suppress concepts, while naive image-guided methods risk over-erasing unrelated content. We propose TICoE, a text-image Collaborative Erasing framework that achieves precise and faithful concept removal through a continuous convex concept manifold and hierarchical visual representation learning. TICoE precisely removes target concepts while preserving unrelated semantic and visual content. To objectively assess the quality of erasure, we further introduce a fidelity-oriented evaluation strategy that measures post-erasure usability. Experiments on multiple benchmarks show that TICoE surpasses prior methods in concept removal precision and content fidelity, enabling safer, more controllable text-to-image generation. Our code is available at https://github.com/OpenAscent-L/TICoE.git

Recent zero-shot Text-to-Speech (TTS) systems can clone previously unseen voices from only a few seconds of audio. We formulate Speech Generation Speaker Poisoning (SGSP), a task that seeks to prevent a model from synthesizing targeted speaker identities while maintaining performance on all other speakers. Unlike conventional machine unlearning, removing training examples is insufficient because modern zero-shot TTS systems can reconstruct identities through learned speaker representations and strong generalization capabilities. We evaluate both inference-time filtering and parameter-modification approaches across settings involving 1, 15, and 100 forget speakers, focusing primarily on speakers seen during training, which we show are harder to suppress than unseen speakers. To characterize the trade-off between utility and privacy, we introduce an evaluation framework based on AUC analysis and a proposed metric, Forget Set Similarity (FSSIM). Our results demonstrate effective speaker suppression for up to 15 forget speakers while revealing that worst-case identity leakage (Max-FSSIM) remains unresolved at multi-speaker scale - establishing this as an open challenge for future work. Together, our work establishes targeted speaker poisoning as a task for zero-shot TTS and, using StyleTTS2 as an initial testbed, provides methods and evaluation protocols for future research, with code and model weights.

Unlearning knowledge is a pressing and challenging task in Large Language Models (LLMs) because of their unprecedented capability to memorize and digest training data at scale, raising more significant issues regarding safety, privacy, and intellectual property. However, existing works, including parameter editing, fine-tuning, and distillation-based methods, are all focused on flat sentence-level data but overlook the relational, multi-hop, and reasoned knowledge in naturally structured data. In response to this gap, this paper introduces Graph Oblivion and Node Erasure (GONE), a benchmark for evaluating knowledge unlearning over structured knowledge graph (KG) facts in LLMs.This KG-based benchmark enables the disentanglement of three effects of unlearning: direct fact removal, reasoning-based leakage, and catastrophic forgetting. In addition, Neighborhood-Expanded Distribution Shaping (NEDS), a novel unlearning framework, is designed to leverage graph connectivity and identify anchor-correlated neighbors, thereby enforcing a precise semantic separation between the forgotten fact and its semantic neighborhood. Evaluations on LLaMA-3-8B and Mistral-7B across multiple knowledge editing and unlearning methods showcase NEDS's superior performance (1.000 on unlearning efficacy and 0.839 on locality) on GONE and other benchmarks. The dataset is available at https://huggingface.co/datasets/GONE-Anonymous/GONE.

Knowledge editing (KE) offers a lightweight alternative to retraining for updating large language models (LLMs). Meanwhile, fine-tuning remains the default operation for adapting LLMs to new domains and tasks. Despite their widespread adoption, these two post-training interventions have been studied in isolation, leaving open a crucial question: if we fine-tune an edited model, do the edits survive? This question is motivated by practical objectives: removing covert or malicious edits, and preserving beneficial edits. If fine-tuning impairs edits (Fig.1), current KE methods become less efficient, as a newly fine-tuned model requires re-editing; if edits persist, fine-tuned models risk propagating hidden malicious edits, raising serious safety concerns. To this end, we systematically quantify edit decay after fine-tuning across 254 experimental configurations. Our results show that in general, edits decay substantially after subsequent fine-tuning. AlphaEdit exhibits the greatest decay on the zsRE benchmark when applied to GPT-J, where 25.27% of previously successful edits become unsuccessful after fine-tuning. We further find that fine-tuning only the edited layers is sufficient to effectively remove edits, while incurring only modest degradation in downstream performance. Surprisingly, fine-tuning non-edited layers leads to greater edit decay than all-layer fine-tuning. Besides, our activation space analysis reveals that fine-tuning produces a larger and more coherent representational shift, both in magnitude and direction, than KE. Overall, our study underscores the necessity of evaluating KE within the broader LLM application pipeline.

Concept erasure methods aim to remove specific unsafe target concepts in diffusion models while preserving image generation utility. To address the vulnerability that erased concepts can be easily recovered under adversarial attacks, adversarial concept erasure methods integrate adversarial optimization into the concept erasure process. However, existing adversarial concept erasure methods face a trade-off between robustness and computational cost. We attribute this to adversarial optimization techniques that use random samples to approximate the adversarial objective function. Adversarial optimization that uses a small number of samples fails to produce adversarial embeddings that accurately capture the target concept space. To mitigate this limitation, we propose Semantic-Guided Adversarial Optimization, which uses a single sample to produce adversarial embeddings that better capture the target concept space. We also propose Semantic-Guided Concept Erasure, which automatically maps the target concept to a semantically similar surrogate. Extensive experiments on not-safe-for-work content, artistic styles, and object-related concepts demonstrate that our method, S-GRACE (Semantic-Guided Robust Adversarial Concept Erasure) achieves state-of-the-art erasure robustness and superior image generation utility, with significantly lower computational cost than existing methods. Our code is available at https://github.com/Qhong-522/S-GRACE.

The proliferation of Low-Rank Adaptation (LoRA) models has democratized personalized text-to-image generation, enabling users to share lightweight models (e.g., personal portraits) on platforms like Civitai and Liblib. However, this "share-and-play" ecosystem introduces critical risks: benign LoRAs can be weaponized by adversaries to generate harmful content (e.g., political, defamatory imagery), undermining creator rights and platform safety. Existing defenses like concept-erasure methods focus on full diffusion models (DMs), neglecting LoRA's unique role as a modular adapter and its vulnerability to adversarial prompt engineering. To bridge this gap, we propose LoRAShield, the first data-free editing framework for securing LoRA models against misuse. Our platform-driven approach dynamically edits and realigns LoRA's weight subspace via adversarial optimization and semantic augmentation. Experimental results demonstrate that LoRAShield achieves remarkable effectiveness, efficiency, and robustness in blocking malicious generations without sacrificing the functionality of the benign task. By shifting the defense to platforms, LoRAShield enables secure, scalable sharing of personalized models, a critical step toward trustworthy generative ecosystems.

Retrieval-Augmented Generation (RAG) is a promising technique for applying LLMs to proprietary domains. However, retrieved documents may contain sensitive knowledge, posing risks of privacy leakage in generative results. Thus, effectively erasing private information from retrieved documents is a key challenge for RAG. Unlike traditional text anonymization, RAG should consider: (1) the inherent multi-document reasoning may face de-anonymization attacks; (2) private knowledge varies by scenarios, so users should be allowed to customize which information to erase; (3) preserving sufficient publicly available knowledge for generation tasks. This paper introduces the privacy erasure task for RAG and proposes Eraser4RAG, a private knowledge eraser which effectively removes user-defined private knowledge from documents while preserving sufficient public knowledge for generation. Specifically, we first construct a global knowledge graph to identify potential knowledge across documents, aiming to defend against de-anonymization attacks. Then we randomly split it into private and public sub-graphs, and fine-tune Flan-T5 to rewrite the retrieved documents excluding private triples. Finally, PPO algorithm optimizes the rewriting model to minimize private triples and maximize public triples retention. Experiments on four QA datasets demonstrate that Eraser4RAG achieves superior erase performance than GPT-4o.

Text-to-image diffusion models have gained widespread application across various domains, demonstrating remarkable creative potential. However, the strong generalization capabilities of diffusion models can inadvertently lead to the generation of not-safe-for-work (NSFW) content, posing significant risks to their safe deployment. While several concept erasure methods have been proposed to mitigate the issue associated with NSFW content, a comprehensive evaluation of their effectiveness across various scenarios remains absent. To bridge this gap, we introduce a full-pipeline toolkit specifically designed for concept erasure and conduct the first systematic study of NSFW concept erasure methods. By examining the interplay between the underlying mechanisms and empirical observations, we provide in-depth insights and practical guidance for the effective application of concept erasure methods in various real-world scenarios, with the aim of advancing the understanding of content safety in diffusion models and establishing a solid foundation for future research and development in this critical area.