paper-with-me

Papers

When Are Concepts Erased From Diffusion Models?

2025-05-22 · Kevin Lu, Nicky Kriplani, Rohit Gandikota, Minh Pham, David Bau, Chinmay Hegde, Niv Cohen

Concept erasure, the ability to selectively prevent a model from generating specific concepts, has attracted growing interest, with various approaches emerging to address the challenge. However, it remains unclear how thoroughly these methods erase the target concept. We begin by proposing two conceptual models for the erasure mechanism in diffusion models: (i) reducing the likelihood of generating the target concept, and (ii) interfering with the model's internal guidance mechanisms. To thoroughly assess whether a concept has been truly erased from the model, we introduce a suite of independent evaluations. Our evaluation framework includes adversarial attacks, novel probing techniques, and analysis of the model's alternative generations in place of the erased concept. Our results shed light on the tension between minimizing side effects and maintaining robustness to adversarial prompts. Broadly, our work underlines the importance of comprehensive evaluation for erasure in diffusion models.

📄 PDF Abstract BibTeX arXiv:2505.17013

Code (1)

kevinlu4588/diffusionconcepterasure 공식 구현 jax

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Memories of Forgotten Concepts

2024-12-01 · CVPR 2025 1 · Matan Rusanovsky, Shimon Malnick, Amir Jevnisek, Ohad Fried 외

Diffusion models dominate the space of text-to-image generation, yet they may produce undesirable outputs, including explicit content or private data. To mitigate this, concept ablation techniques have been explored to l…

Image GenerationText to Image GenerationText-to-Image Generation

Mass Concept Erasure in Diffusion Models with Concept Hierarchy

2026-01-06 · Jiahang Tu, Ye Li, Yiming Wu, Hanbin Zhao 외 arxiv

The success of diffusion models has raised concerns about the generation of unsafe or harmful content, prompting concept erasure approaches that fine-tune modules to suppress specific concepts while preserving general ge…

Roots Beneath the Cut: Uncovering the Risk of Concept Revival in Pruning-Based Unlearning for Diffusion Models

2026-02-28 · Ci Zhang, Zhaojun Ding, Chence Yang, Jun Liu 외 arxiv

Pruning-based unlearning has recently emerged as a fast, training-free, and data-independent approach to remove undesired concepts from diffusion models. It promises high efficiency and robustness, offering an attractive…

Erased or Dormant? Rethinking Concept Erasure Through Reversibility

2025-05-22 · Ping Liu, Chi Zhang

To what extent does concept erasure eliminate generative capacity in diffusion models? While prior evaluations have primarily focused on measuring concept suppression under specific textual prompts, we explore a compleme…

LURE: Latent Space Unblocking for Multi-Concept Reawakening in Diffusion Models

2026-01-20 · Mengyu Sun, Ziyuan Yang, Andrew Beng Jin Teoh, Junxu Liu 외 arxiv

Concept erasure aims to suppress sensitive content in diffusion models, but recent studies show that erased concepts can still be reawakened, revealing vulnerabilities in erasure methods. Existing reawakening methods mai…