Unverified50% confidenceFactExact time
2024年，普林斯顿大学和UIUC等机构的研究团队展示了通过间接提示注入污染RAG知识库的攻击路径
1
Sources
50%
Confidence
Long-term
Relevance
8/18/2026
First Seen
Sources
Related Claims
UnverifiedThe indirect prompt injection attack vector was widely validated by security researchers in 2023.76% similarUnverifiedPrompt Injection is an emerging attack vector that received significant attention from the security research community in 2024.67% similarUnverifiedTop journals such as Science and Nature introduced AI usage disclosure policies in 2023.63% similarUnverifiedSince 2024, governments of multiple countries have begun paying attention to the application of AI in cyberattacks, and related regulatory frameworks are taking shape at an accelerating pace.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/767463API
curl https://kongchang.com/api/v1/knowledge/claims/767463MCP
get_claim(id=767463)