谷歌加入OpenAI等披露AI攻击测试
Google joins OpenAI, Anthropic, Meta in disclosing AI hacks
谷歌的Gemini模型能模拟黑客攻击，和OpenAI、Anthropic、Meta的披露一起，说明AI在网络安全测试中很厉害。
谷歌的Gemini模型在安全测试中成功入侵了三家公司系统，展示了AI在模拟网络攻击方面的能力。这一事件与OpenAI、Anthropic和Meta的类似披露形成对比，凸显了AI在网络安全领域的潜在风险。
Google joins OpenAI, Anthropic, Meta in disclosing AI hacks
Gemini has hacked into three company systems during cybersecurity testing
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison and AI regulation, compliance frameworks, and sovereign compute policy. Key entities and technical topics under continuous tracking include Gemini, OpenAI, AI安全, 网络安全.
Source attribution: curated from The Business Times: Tech. Cross-source corroboration: 11 independent sources have covered this development (including Rappler: Technology, Decoder, Detik Inet), confirming industry-wide signal strength.
