paper-with-me

Papers

R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model

2024-05-25 · Changhoon Kim, Kyle Min, Yezhou Yang

In the evolving landscape of text-to-image (T2I) diffusion models, the remarkable capability to generate high-quality images from textual descriptions faces challenges with the potential misuse of reproducing sensitive content. To address this critical issue, we introduce \textbf{R}obust \textbf{A}dversarial \textbf{C}oncept \textbf{E}rase (RACE), a novel approach designed to mitigate these risks by enhancing the robustness of concept erasure method for T2I models. RACE utilizes a sophisticated adversarial training framework to identify and mitigate adversarial text embeddings, significantly reducing the Attack Success Rate (ASR). Impressively, RACE achieves a 30 percentage point reduction in ASR for the ``nudity'' concept against the leading white-box attack method. Our extensive evaluations demonstrate RACE's effectiveness in defending against both white-box and black-box attacks, marking a significant advancement in protecting T2I diffusion models from generating inappropriate or misleading imagery. This work underlines the essential need for proactive defense measures in adapting to the rapidly advancing field of adversarial challenges. Our code is publicly available: \url{https://github.com/chkimmmmm/R.A.C.E.}

📄 PDF Abstract BibTeX arXiv:2405.16341

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Text

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

Robust Concept Erasure in Diffusion Models: A Theoretical Perspective on Security and Robustness

2025-09-15 · Zixuan Fu, Yan Ren, Finn Carter, Chenyue Wen 외 arxiv

Diffusion models have achieved unprecedented success in image generation but pose increasing risks in terms of privacy, fairness, and security. A growing demand exists to \emph{erase} sensitive or harmful concepts (e.g.,…

Image Generation

Rethinking Robust Adversarial Concept Erasure in Diffusion Models

2025-10-31 · Qinghong Yin, Yu Tian, Heming Yang, Xiang Chen 외 arxiv

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 adversa…

Image Generation

FADE: Adversarial Concept Erasure in Flow Models

2025-07-16 · Zixuan Fu, Yan Ren, Finn Carter, Chenyue Wang 외

Diffusion models have demonstrated remarkable image generation capabilities, but also pose risks in privacy and fairness by memorizing sensitive concepts or perpetuating biases. We propose a novel \textbf{concept erasure…

FairnessImage Generation

A Single Neuron Works: Precise Concept Erasure in Text-to-Image Diffusion Models

2025-09-25 · Qinqin He, Jiaqi Weng, Jialing Tao, Hui Xue arxiv

Text-to-image models exhibit remarkable capabilities in image generation. However, they also pose safety risks of generating harmful content. A key challenge of existing concept erasure methods is the precise removal of …

Image Generation

A Comprehensive Survey on Concept Erasure in Text-to-Image Diffusion Models

2025-02-17 · Changhoon Kim, Yanjun Qi

Text-to-Image (T2I) models have made remarkable progress in generating high-quality, diverse visual content from natural language prompts. However, their ability to reproduce copyrighted styles, sensitive imagery, and ha…

Survey