Unverified60% confidenceFactExact time
In 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.
2
Sources
60%
Confidence
Long-term
Relevance
7/15/2026
First Seen
Sources
Related Claims
UnverifiedIndirect Prompt Injection was systematically elaborated by security researcher Kai Greshake and colleagues in a 2023 paper.77% similarUnverified2023年卡内基梅隆大学与德国CISPA亥姆霍兹信息安全中心的研究团队发表论文，证明当时主流LLM Agent对间接提示注入攻击高度脆弱，成功率超过80%70% similarUnverified研究人员Kai Greshake等人在2023年发表的论文《Not What You've Signed Up For》系统性地揭示了间接提示注入的威胁模型70% similarUnverified依赖混淆攻击由安全研究员Alex Birsan于2021年首次公开披露68% similarUnverifiedPrompt injection attacks were first systematically described in 2022 by security researcher Simon Willison.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/515084API
curl https://kongchang.com/api/v1/knowledge/claims/515084MCP
get_claim(id=515084)