Unverified50% confidenceFactExact time
By 2023, academia had demonstrated multiple attack vectors against RAG systems, including knowledge conflict attacks and backdoor trigger attacks.
1
Sources
50%
Confidence
Long-term
Relevance
9/7/2026
First Seen
Sources
Related Entities
Related Claims
Unverified2024年多项学术研究展示了记忆投毒攻击在基于RAG的Agent系统中的可行性，包括通过间接提示注入污染检索语料库的攻击方式72% similarUnverified2023年卡内基梅隆大学发表的对抗性攻击论文表明，即便是最先进的安全系统也存在可被系统性利用的盲点72% similarUnverifiedBetween 2023 and 2024, security researchers discovered malicious models on the Hugging Face platform multiple times, with attackers executing attacks by embedding malicious code in model serialization files.65% similarUnverifiedBy 2024, security researchers had demonstrated indirect prompt injection attacks that hijack RAG system outputs by embedding hidden instructions in web pages64% similarUnverifiedSince 2024, multimodal jailbreak attacks have begun to emerge, with attackers embedding malicious instructions in images or audio to bypass text-level safety detection.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/869932API
curl https://kongchang.com/api/v1/knowledge/claims/869932MCP
get_claim(id=869932)