Unverified50% confidenceFactExact time
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
1
Sources
50%
Confidence
Long-term
Relevance
7/13/2026
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70% similarVerifiedResidual connections were originally proposed by He et al. in the 2015 ResNet paper to address the vanishing gradient problem in deep neural networks.69% similarUnverified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65% similarUnverified怀尔斯1993年提交费马大定理证明后被发现存在一处关键漏洞，涉及欧拉系统归纳步骤的隐含假设63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/501428API
curl https://kongchang.com/api/v1/knowledge/claims/501428MCP
get_claim(id=501428)