Unverified50% confidenceFactExact time
Adversarial sample attacks can add noise to images that is nearly imperceptible to the human eye yet causes models to produce incorrect classifications
1
Sources
50%
Confidence
Long-term
Relevance
9/10/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedAfter 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.80% similarUnverifiedAdversarial attacks targeting specific detectors can fool detection models by adding imperceptibly small perturbations to generated content.79% similarUnverifiedThe concept of adversarial examples was first systematically articulated by Ian Goodfellow et al. in 2014, demonstrating that adding imperceptibly small perturbations to images in the computer vision domain can cause classifiers to produce incorrect judgments.73% similarUnverifiedShifting an image by one pixel can cause a CNN model's recognition result to change drastically or even fail completely.73% 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72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/885991API
curl https://kongchang.com/api/v1/knowledge/claims/885991MCP
get_claim(id=885991)