M-ErasureBench: A Comprehensive Multimodal Evaluation Benchmark for Concept Erasure in Diffusion Models

• URL: http://arxiv.org/abs/2512.22877v1
• Date: Sun, 28 Dec 2025 10:58:36 GMT
• Title: M-ErasureBench: A Comprehensive Multimodal Evaluation Benchmark for Concept Erasure in Diffusion Models
• Abstract summary: M-ErasureBench is a novel framework that benchmarks concept erasure methods across three input modalities.<n> IRECE is a plug-and-play module that localizes target concepts via cross-attention and perturbs the associated latents during denoising.
• Score: 13.885985776728559
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-image diffusion models may generate harmful or copyrighted content, motivating research on concept erasure. However, existing approaches primarily focus on erasing concepts from text prompts, overlooking other input modalities that are increasingly critical in real-world applications such as image editing and personalized generation. These modalities can become attack surfaces, where erased concepts re-emerge despite defenses. To bridge this gap, we introduce M-ErasureBench, a novel multimodal evaluation framework that systematically benchmarks concept erasure methods across three input modalities: text prompts, learned embeddings, and inverted latents. For the latter two, we evaluate both white-box and black-box access, yielding five evaluation scenarios. Our analysis shows that existing methods achieve strong erasure performance against text prompts but largely fail under learned embeddings and inverted latents, with Concept Reproduction Rate (CRR) exceeding 90% in the white-box setting. To address these vulnerabilities, we propose IRECE (Inference-time Robustness Enhancement for Concept Erasure), a plug-and-play module that localizes target concepts via cross-attention and perturbs the associated latents during denoising. Experiments demonstrate that IRECE consistently restores robustness, reducing CRR by up to 40% under the most challenging white-box latent inversion scenario, while preserving visual quality. To the best of our knowledge, M-ErasureBench provides the first comprehensive benchmark of concept erasure beyond text prompts. Together with IRECE, our benchmark offers practical safeguards for building more reliable protective generative models.

Related papers

• Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models [105.53190946111586]
  We term this phenomenon object-dependent concept brittleness.<n>We present an interpretability-oriented framework to audit and minimally correct these failures.<n>We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones.
  arXiv  Detail & Related papers  (2026-09-09T09:07:40Z)
• Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion Models [30.409877438368724]
  Large-scale text-to-image (T2I) diffusion models pose safety risks due to their capacity to reproduce undesirable content, such as copyrighted ones.<n> Concept erasure has emerged as a mitigation strategy, yet existing approaches struggle to balance scalability, precision, and robustness.<n>We present Erasing Thousands of Concepts (ETC), a scalable framework capable of erasing thousands of concepts while preserving generation quality.
  arXiv  Detail & Related papers  (2026-04-12T10:39:41Z)
• TINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Models [92.56562999211809]
  A text-centric paradigm equates erasure with severing the text-to-image mapping, ignoring that the underlying visual knowledge related to undesired concepts still persist.<n>We introduce Tina, a novel Text-free INversion Attack, which enforces this visual-only probe by operating under a null-text condition.<n>Our experiments demonstrate that Tina regenerates erased concepts from models treated with state-of-the-art unlearning.
  arXiv  Detail & Related papers  (2026-03-18T15:25:03Z)
• Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition [81.2779530670268]
  Vision-Language Models (VLMs) have significantly advanced zero-shot image recognition.<n>This paper enhances prompt by incorporating class-specific concepts.<n>Our method consistently outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-03-09T03:11:11Z)
• CGCE: Classifier-Guided Concept Erasure in Generative Models [53.7410000675294]
  Concept erasure has been developed to remove undesirable concepts from pre-trained models.<n>Existing methods remain vulnerable to adversarial attacks that can regenerate the erased content.<n>We introduce an efficient plug-and-play framework that provides robust concept erasure for diverse generative models.
  arXiv  Detail & Related papers  (2025-11-08T05:38:18Z)
• Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models [27.672305802461377]
  We introduce a novel training-free, zero-shot framework for concept erasure that operates directly on text embeddings before the diffusion process.<n>We achieve superior completeness and robustness while preserving locality and image quality.<n>This robustness also allows our framework to function as a built-in threat detection system, offering a practical solution for safer text-to-image generation.
  arXiv  Detail & Related papers  (2025-10-26T22:04:17Z)
• Robust Concept Erasure in Diffusion Models: A Theoretical Perspective on Security and Robustness [4.23067546195708]
  textbfSCORE (Secure and Concept-Oriented Robust Erasure) is a novel framework for robust concept removal in diffusion models.<n>SCORE sets a new standard for secure and robust concept erasure in diffusion models.
  arXiv  Detail & Related papers  (2025-09-15T15:05:50Z)
• Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning [28.15997901023315]
  Recall is a novel adversarial framework designed to compromise the robustness of unlearned IGMs.<n>It consistently outperforms existing baselines in terms of adversarial effectiveness, computational efficiency, and semantic fidelity with the original prompt.<n>These findings reveal critical vulnerabilities in current unlearning mechanisms and underscore the need for more robust solutions.
  arXiv  Detail & Related papers  (2025-07-09T02:59:01Z)
• 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)
• Erasing More Than Intended? How Concept Erasure Degrades the Generation of Non-Target Concepts [31.232389877218377]
  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.
  arXiv  Detail & Related papers  (2025-01-16T20:42:17Z)
• On the Fairness, Diversity and Reliability of Text-to-Image Generative Models [68.62012304574012]
  multimodal generative models have sparked critical discussions on their reliability, fairness and potential for misuse.<n>We propose an evaluation framework to assess model reliability by analyzing responses to global and local perturbations in the embedding space.<n>Our method lays the groundwork for detecting unreliable, bias-injected models and tracing the provenance of embedded biases.
  arXiv  Detail & Related papers  (2024-11-21T09:46:55Z)
• 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.<n>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.<n> 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)
• Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models? [52.238883592674696]
  Ring-A-Bell is a model-agnostic red-teaming tool for T2I diffusion models. It identifies problematic prompts for diffusion models with the corresponding generation of inappropriate content. Our results show that Ring-A-Bell, by manipulating safe prompting benchmarks, can transform prompts that were originally regarded as safe to evade existing safety mechanisms.
  arXiv  Detail & Related papers  (2023-10-16T02:11:20Z)

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.