Unverified50% confidenceFactExact time
图像对抗攻击中，人类视觉系统是低频感知主导对高频微小扰动不敏感，而CNN（卷积神经网络）对高频纹理特征高度敏感，这一感知鸿沟造成了人眼正常、AI认错的现象
1
Sources
50%
Confidence
Long-term
Relevance
7/13/2026
First Seen
Sources
Related Claims
Unverified目视间隔的根本弱点在于将系统安全的关键环节建立在人类视觉感知这一高度易错的能力之上，尤其在夜间、雨雾天气或复杂灯光环境中73% similarUnverifiedAfter superimposing tiny perturbations that are nearly invisible to the human eye onto an image correctly classified by a neural network, the model output will produce an error with extremely high confidence.72% similarUnverifiedConvolutional Neural Networks (CNNs), inspired by the structure of the visual cortex, extract local features by sliding convolutional kernels across images, with the parameter sharing mechanism significantly reducing computational load.72% similarUnverified反AI字体引入的是人眼可轻松忽略、却足以干扰机器识别流程的视觉噪声，与传统对抗攻击方向相反71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/501749API
curl https://kongchang.com/api/v1/knowledge/claims/501749MCP
get_claim(id=501749)