[KongchangAI]
Unverified50% confidenceBenchmarkExact time

2024年的研究表明,即使经过专门的安全对齐训练,主流模型对精心构造的注入攻击的防御成功率仍不足90%

1
Sources
50%
Confidence
Long-term
Relevance
8/22/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/786461
API
curl https://kongchang.com/api/v1/knowledge/claims/786461
MCP
get_claim(id=786461)