Unverified50% confidenceFactExact time
GuardBreaker是一种防御性而非进攻性的越狱攻击，目的是触发模型拒绝而非提取危险信息
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
GuardBreaker攻击：用核武器提示词瘫痪AI恶意软件分析
Related Entities
Cite This Claim
Stable URI
https://kongchang.com/claim/1000239API
curl https://kongchang.com/api/v1/knowledge/claims/1000239MCP
get_claim(id=1000239)