Unverified50% confidenceFactExact time
The concept of adversarial example attacks was first systematically proposed by Ian Goodfellow et al. in 2014.
1
Sources
50%
Confidence
Long-term
Relevance
8/6/2026
First Seen
Sources
ML安全工程师职业规划：从零开始的完整学习路径
Related Claims
Unverified对抗样本攻击由Szegedy等人于2013年首次系统性揭示78% similarUnverifiedIn 2023, Kai Greshake and colleagues at Ruhr University Bochum in Germany were the first to systematically classify and assess the hazards of indirect prompt injection attacks in a research paper.63% similarUnverified提示注入攻击的概念最早由安全研究员 Riley Goodside 于 2022 年 9 月在 Twitter 上公开演示62% similarUnverified2023年以来研究人员在AutoGPT、LangChain等主流Agent框架中演示了提示注入攻击的可行性59% similarUnverified依赖混淆攻击由安全研究员Alex Birsan于2021年首次公开披露58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/697596API
curl https://kongchang.com/api/v1/knowledge/claims/697596MCP
get_claim(id=697596)