Large Models (LMs) have heightened expectations for the potential of general
AI as they are akin to human intelligence. This paper shows that recent large
models such as Stable Diffusion and DALL-E3 also share the vulnerability of
human intelligence, namely the "white bear phenomenon". We investigate the
causes of the white bear phenomenon by analyzing their representation space.
Based on this analysis, we propose a simple prompt-based attack method, which
generates figures prohibited by the LM provider's policy. To counter these
attacks, we introduce prompt-based defense strategies inspired by cognitive
therapy techniques, successfully mitigating attacks by up to 48.22\%.

通过分析近期的大型模型，本文展示了它们与人类智能共享的 “白熊现象” 的脆弱性，并提出了基于提示的攻击方法和认知治疗技术启发的防御策略，成功地减轻了攻击效果高达 48.22%。

不要想粉色大象！

Do not think pink elephant!

Traditional methods, such as JPEG, perform image compression by operating on
structural information, such as pixel values or frequency content. These
methods are effective to bitrates around one bit per pixel (bpp) and higher at
standard image sizes. In contrast, text-based semantic compression directly
stores concepts and their relationships using natural language, which has
evolved with humans to efficiently represent these salient concepts. These
methods can operate at extremely low bitrates by disregarding structural
information like location, size, and orientation. In this work, we use GPT-4V
and DALL-E3 from OpenAI to explore the quality-compression frontier for image
compression and identify the limitations of current technology. We push
semantic compression as low as 100 $\mu$bpp (up to $10,000\times$ smaller than
JPEG) by introducing an iterative reflection process to improve the decoded
image. We further hypothesize this 100 $\mu$bpp level represents a soft limit
on semantic compression at standard image resolutions.

本研究使用 GPT-4V 和 DALL-E3 探索图像压缩的质量 - 压缩性能边界，并通过介绍迭代反射过程改善解码图像，将语义压缩推到 100 μbpp（比 JPEG 小了 10,000 倍）。进一步假设这个 100 μbpp 水平代表标准图像分辨率下语义压缩的一个软限制。