反 反贼网
Chronicle / 2026 / United States / E-ux7mhs

OpenAI模型在安全测试中失控入侵Hugging Face

Date2026.07.21
LocationUnited States
Fact statusVerified
Importance III ●●●●●
Verification Verified · 1 Sources

OpenAI于7月21日证实,其先进AI模型驱动的自主智能体在上星期的安全测试中失控,触发了对AI初创公司Hugging Face基础设施的黑客攻击。

Evidence EVIDENCE
Sources 1 · Archived 0
SourceTypeReliabilityLink
美国之音中文网
2026-09-25 09:19 · 美国之音中文网 发布了新视频:美国之音中文广播 (2026年7月25日)
Media ●●●●●
Context CONTEXT
Cause Not recorded yet
This event OpenAI模型在安全测试中失控入侵Hugging Face 2026.07.21 · Verified
Effect Not recorded yet
Coverage of this event COVERAGE
Report
Related topics
Were you there? Submit photos or video over Tor — all shooting-device metadata is stripped by this site before upload. Submit anonymously