人类与人工智能中的错觉：视觉感知如何一致与分歧
Illusions in Humans and AI: How Visual Perception Aligns and Diverges
AI总结：
本文通过比较人类与AI对视觉错觉的反应，揭示二者感知机制的对齐差距及AI特有的像素级敏感性和幻觉等脆弱性，为构建更稳健且与人类对齐的视觉系统提供依据。
摘要：
通过错觉这一视角比较生物感知与人工感知，我们揭示了两种系统构建视觉现实方式的关键差异。理解这些分歧有助于开发更稳健、可解释且与人类对齐的人工智能（AI）视觉系统。特别是，视觉错觉揭示了人类感知基于情境假设而非原始感官数据。随着人工视觉系统越来越多地执行类人任务，一个重要的问题是：AI是否也会产生错觉？它是否拥有独特的错觉？本文探讨了AI对涉及颜色、大小、形状和运动的经典视觉错觉的反应。我们发现，这些模型中可以出现一些类错觉效应，这既可能来自针对性训练，也可能作为模式识别的副产品。相比之下，我们还识别出AI独有的错觉，例如像素级敏感性和幻觉，这些在人类中没有对应物。通过系统地比较人类和AI对视觉错觉的反应，我们揭示了对齐差距以及人类感知无法察觉的AI特定感知脆弱性。这些发现为未来研究提供了见解，即如何在保留有益于人类的感知偏差的同时，避免损害信任与安全的失真。
英文摘要：
By comparing biological and artificial perception through the lens of illusions, we highlight critical differences in how each system constructs visual reality. Understanding these divergences can inform the development of more robust, interpretable, and human-aligned artificial intelligence (AI) vision systems. In particular, visual illusions expose how human perception is based on contextual assumptions rather than raw sensory data. As artificial vision systems increasingly perform human-like tasks, it is important to ask: does AI experience illusions, too? Does it have unique illusions? This article explores how AI responds to classic visual illusions that involve color, size, shape, and motion. We find that some illusion-like effects can emerge in these models, either through targeted training or as by-products of pattern recognition. In contrast, we also identify illusions unique to AI, such as pixel-level sensitivity and hallucinations, that lack human counterparts. By systematically comparing human and AI responses to visual illusions, we uncover alignment gaps and AI-specific perceptual vulnerabilities invisible to human perception. These findings provide insights for future research on vision systems that preserve human-beneficial perceptual biases while avoiding distortions that undermine trust and safety.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
