Unverified50% confidenceFactExact time
对抗性样本（Adversarial Examples）的理论基础由Szegedy等人于2013年首次系统阐述
1
Sources
50%
Confidence
Long-term
Relevance
7/20/2026
First Seen
Sources
Related Claims
Unverified对抗性样本的概念最早由Christian Szegedy等人于2013年在论文《Intriguing properties of neural networks》中系统提出75% similarUnverified对抗样本由Goodfellow等人于2014年首次系统描述，其本质是神经网络决策边界的高维非线性裂缝65% similarVerifiedThe theoretical foundations of diffusion models can be traced back to a 2015 paper on non-equilibrium thermodynamics published by Sohl-Dickstein et al.64% similarUnverified框架效应最初由Kahneman和Tversky在前景理论中系统描述61% similarUnverified助推理论由理查德·塞勒和卡斯·桑斯坦在2008年著作《助推》中系统阐述61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/566577API
curl https://kongchang.com/api/v1/knowledge/claims/566577MCP
get_claim(id=566577)