无需训练即可防御生成不当图像的对抗攻击，提升安全检测可靠性。
SC-Pro: Training-Free Framework for Defending Unsafe Image Synthesis Attack
- 利用文本提示或输入潜变量微小变化导致攻击失效的特性，设计无训练防御框架。
- 在多个测试场景中实现接近100%的防御准确率，显著优于现有方法。
- 适用于资源受限环境，支持单步扩散模型快速检测，适合部署于实际系统。
随着扩散模型的发展，图像生成性能显著提升，但也引发了滥用风险，如生成不适宜工作场所（NSFW）内容。为应对这一问题，Stable Diffusion 模型内置多个安全检查机制，用于过滤初始文本提示和生成的最终图像。然而，近期研究发现这些安全机制对对抗攻击存在漏洞，可被用于生成 NSFW 图像。本文发现此类对抗攻击对文本提示或输入潜变量的微小变化缺乏鲁棒性。基于此，我们提出 SC-Pro（Spherical or Circular Probing）——一种无需训练的防御框架，能有效抵御生成 NSFW 图像的对抗攻击。此外，我们还开发了一种基于单步扩散模型的高效检测方法（SC-Pro-o），进一步降低计算开销。实验表明，该方法在性能与适用性方面均表现出色。
原文摘要 · Abstract (English)
With advances in diffusion models, image generation has shown significant performance improvements. This raises concerns about the potential abuse of image generation, such as the creation of explicit or violent images, commonly referred to as Not Safe For Work (NSFW) content. To address this, the Stable Diffusion model includes several safety checkers to censor initial text prompts and final output images generated from the model. However, recent research has shown that these safety checkers have vulnerabilities against adversarial attacks, allowing them to generate NSFW images. In this paper, we find that these adversarial attacks are not robust to small changes in text prompts or input latents. Based on this, we propose SC-Pro (Spherical or Circular Probing), a training-free framework that easily defends against adversarial attacks generating NSFW images. Moreover, we develop an approach that utilizes one-step diffusion models for efficient NSFW detection (SC-Pro-o), further reducing computational resources. We demonstrate the superiority of our method in terms of performance and applicability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。