Unverified50% confidenceFactExact time
A black-box attack refers to an approach where an attacker, without access to a model's internal parameters and architecture, infers its decision boundaries and exploits them solely by repeatedly querying the model's inputs and outputs.
1
Sources
50%
Confidence
Long-term
Relevance
10/10/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedRAG架构引入了间接提示注入攻击面：攻击者只需在RAG检索的数据源中植入恶意指令即可操纵模型68% similarUnverified针对特定触发词的后门攻击可让模型在大多数情况下表现正常，仅在遇到特定输入时才输出预设错误信息，使常规评测基准难以捕捉65% similarUnverified间接提示注入攻击中，攻击者只需在RAG会检索到的数据源中植入恶意指令即可操纵模型，传统WAF无法拦截65% similarUnverified数据投毒攻击按攻击目标可分为可用性攻击和目标攻击，前者旨在降低模型整体性能，后者只在特定触发条件下改变模型行为64% similarUnverified工具调用使攻击面从让模型说错话升级为让模型做错事，危害从信息误导上升为实质性的数据访问和系统篡改63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/994956API
curl https://kongchang.com/api/v1/knowledge/claims/994956MCP
get_claim(id=994956)