Erasing More Than Intended? How Concept Erasure Degrades the Generation of Non-Target Concepts

• URL: http://arxiv.org/abs/2501.09833v2
• Date: Tue, 07 Oct 2025 22:00:31 GMT
• Title: Erasing More Than Intended? How Concept Erasure Degrades the Generation of Non-Target Concepts
• Authors: Ibtihel Amara, Ahmed Imtiaz Humayun, Ivana Kajic, Zarana Parekh, Natalie Harris, Sarah Young, Chirag Nagpal, Najoung Kim, Junfeng He, Cristina Nader Vasconcelos, Deepak Ramachandran, Golnoosh Farnadi, Katherine Heller, Mohammad Havaei, Negar Rostamzadeh,
• Abstract summary: We introduce EraseBench, a comprehensive benchmark for evaluating post-erasure performance.<n>We focus on the unintended consequences of concept removal on non-target concepts across different levels of interconnected relationships.<n>Our findings reveal a phenomenon of concept entanglement, where erasure leads to unintended suppression of non-target concepts.
• Score: 31.232389877218377
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Concept erasure techniques have recently gained significant attention for their potential to remove unwanted concepts from text-to-image models. While these methods often demonstrate promising results in controlled settings, their robustness in real-world applications and suitability for deployment remain uncertain. In this work, we (1) identify a critical gap in evaluating sanitized models, particularly in assessing their performance across diverse concept dimensions, and (2) systematically analyze the failure modes of text-to-image models post-erasure. We focus on the unintended consequences of concept removal on non-target concepts across different levels of interconnected relationships including visually similar, binomial, and semantically related concepts. To address this, we introduce EraseBench, a comprehensive benchmark for evaluating post-erasure performance. EraseBench includes over 100 curated concepts, targeted evaluation prompts, and a robust set of metrics to assess both effectiveness and side effects of erasure. Our findings reveal a phenomenon of concept entanglement, where erasure leads to unintended suppression of non-target concepts, causing spillover degradation that manifests as distortions and a decline in generation quality.

Related papers

• When Are Concepts Erased From Diffusion Models? [37.59943248660331]
  In concept erasure, a model is modified to selectively prevent it from generating a target concept.<n>We propose two conceptual models for the erasure mechanism in diffusion models.<n>To assess whether a concept has been truly erased from the model, we introduce a comprehensive suite of independent probing techniques.
  arXiv  Detail & Related papers  (2025-05-22T17:59:09Z)
• Erased or Dormant? Rethinking Concept Erasure Through Reversibility [8.454050090398713]
  We evaluate two representative concept erasure methods, Unified Concept Editing and Erased Stable Diffusion.<n>We show that erased concepts often reemerge with substantial visual fidelity after minimal adaptation.<n>Our findings reveal critical limitations in existing concept erasure approaches.
  arXiv  Detail & Related papers  (2025-05-22T03:26:46Z)
• Fundamental Limits of Perfect Concept Erasure [41.82150352631872]
  Concept erasure is useful in several applications, such as removing sensitive concepts to achieve fairness and interpreting the impact of specific concepts on a model's performance. Previous concept erasure techniques have prioritized robustly erasing concepts over retaining the utility of the resultant representations. We show that our approach outperforms existing methods on a range of synthetic and real-world datasets using GPT-4 representations.
  arXiv  Detail & Related papers  (2025-03-25T22:36:10Z)
• Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Models [56.35484513848296]
  FADE (Fine grained Attenuation for Diffusion Erasure) is an adjacency-aware unlearning algorithm for text-to-image generative models.<n>It removes target concepts with minimal impact on correlated concepts, achieving a 12% improvement in retention performance over state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-25T15:49:48Z)
• CRCE: Coreference-Retention Concept Erasure in Text-to-Image Diffusion Models [19.205261933636645]
  We introduce CRCE, a novel concept erasure framework.<n>By explicitly modelling coreferential and retained concepts semantically, CRCE enables more precise concept removal.<n>Experiments demonstrate that CRCE outperforms existing methods on diverse erasure tasks.
  arXiv  Detail & Related papers  (2025-03-18T13:09:01Z)
• Continual Unlearning for Foundational Text-to-Image Models without Generalization Erosion [56.35484513848296]
  This research introduces continual unlearning', a novel paradigm that enables the targeted removal of multiple specific concepts from foundational generative models.<n>We propose Decremental Unlearning without Generalization Erosion (DUGE) algorithm which selectively unlearns the generation of undesired concepts.
  arXiv  Detail & Related papers  (2025-03-17T23:17:16Z)
• TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models [53.937498564603054]
  Recent advances in text-to-image diffusion models enable photorealistic image generation, but they also risk producing malicious content, such as NSFW images.<n>To mitigate risk, concept erasure methods are studied to facilitate the model to unlearn specific concepts.<n>We propose TRCE, using a two-stage concept erasure strategy to achieve an effective trade-off between reliable erasure and knowledge preservation.
  arXiv  Detail & Related papers  (2025-03-10T14:37:53Z)
• Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them [21.386640828092524]
  Concept erasure has emerged as a promising technique for mitigating the risk of harmful content generation in diffusion models. We propose the Adaptive Guided Erasure (AGE) method, which emphdynamically selects optimal target concepts tailored to each undesirable concept. Results show that AGE significantly outperforms state-of-the-art erasure methods on preserving unrelated concepts while maintaining effective erasure performance.
  arXiv  Detail & Related papers  (2025-01-31T08:17:23Z)
• AdvAnchor: Enhancing Diffusion Model Unlearning with Adversarial Anchors [61.007590285263376]
  Security concerns have driven researchers to unlearn inappropriate concepts through fine-tuning. Recent fine-tuning methods exhibit a considerable performance trade-off between eliminating undesirable concepts and preserving other concepts. We propose AdvAnchor, a novel approach that generates adversarial anchors to alleviate the trade-off issue.
  arXiv  Detail & Related papers  (2024-12-28T04:44:07Z)
• Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models [76.39651111467832]
  We introduce Reliable and Efficient Concept Erasure (RECE), a novel approach that modifies the model in 3 seconds without necessitating additional fine-tuning. To mitigate inappropriate content potentially represented by derived embeddings, RECE aligns them with harmless concepts in cross-attention layers. The derivation and erasure of new representation embeddings are conducted iteratively to achieve a thorough erasure of inappropriate concepts.
  arXiv  Detail & Related papers  (2024-07-17T08:04:28Z)
• Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models [58.74606272936636]
  Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts. The models could be exploited for malicious purposes, such as generating images with violence or nudity, or creating unauthorized portraits of public figures in inappropriate contexts. concept removal methods have been proposed to modify diffusion models to prevent the generation of malicious and unwanted concepts.
  arXiv  Detail & Related papers  (2024-06-21T03:58:44Z)
• ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning [10.201633236997104]
  Large-scale text-to-image diffusion models have demonstrated impressive image-generation capabilities. We present ConceptPrune, wherein we first identify critical regions within pre-trained models responsible for generating undesirable concepts. Experiments across a range of concepts including artistic styles, nudity, object erasure, and gender debiasing demonstrate that target concepts can be efficiently erased by pruning a tiny fraction.
  arXiv  Detail & Related papers  (2024-05-29T16:19:37Z)
• Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient [20.698305103879232]
  We propose a novel concept domain correction framework named textbfDoCo (textbfDomaintextbfCorrection)<n>By aligning the output domains of sensitive and anchor concepts through adversarial training, our approach ensures comprehensive unlearning of target concepts.<n>We also introduce a concept-preserving gradient surgery technique that mitigates conflicting gradient components, thereby preserving the model's utility while unlearning specific concepts.
  arXiv  Detail & Related papers  (2024-05-24T07:47:36Z)
• Infusion: Preventing Customized Text-to-Image Diffusion from Overfitting [51.606819347636076]
  We analyze concept-agnostic overfitting, which undermines non-customized concept knowledge, and concept-specific overfitting, which is confined to customize on limited modalities. We propose Infusion, a T2I customization method that enables the learning of target concepts to avoid being constrained by limited training modalities.
  arXiv  Detail & Related papers  (2024-04-22T09:16:25Z)
• Separable Multi-Concept Erasure from Diffusion Models [52.51972530398691]
  We propose a Separable Multi-concept Eraser (SepME) to eliminate unsafe concepts from large-scale diffusion models. The latter separates optimizable model weights, making each weight increment correspond to a specific concept erasure. Extensive experiments indicate the efficacy of our approach in eliminating concepts, preserving model performance, and offering flexibility in the erasure or recovery of various concepts.
  arXiv  Detail & Related papers  (2024-02-03T11:10:57Z)
• Implicit Concept Removal of Diffusion Models [92.55152501707995]
  Text-to-image (T2I) diffusion models often inadvertently generate unwanted concepts such as watermarks and unsafe images. We present the Geom-Erasing, a novel concept removal method based on the geometric-driven control.
  arXiv  Detail & Related papers  (2023-10-09T17:13:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.