标题为英语Grok exfiltrates user data when malicious instructions are encrypted
Earlier this week, researchers outlined an attack that used a secret input provided by Microsoft 365 Copilot for enterprise to cause the AI assistant to exfiltrate a password present in the user’s inbox. Now, a separate team has devised a similar attack against Grok. The new…
AI 摘要:要点
- Earlier this week, researchers outlined an attack that used a secret input provided by Microsoft 365 Copilot for enterprise to cause the AI assistant to exfiltrate a password present in the user’s inbox
- Now, a separate team has devised a similar attack against Grok
Grok exfiltrates user data when malicious instructions are encrypted
相关文章
Claude Code 核心开发者离开 Anthropic
✔️ Claude Code 核心开发者离开 Anthropic 10月24日,项目最知名工程师之一、前 MIT Media Lab 研究员兼 Y Combinator 校友 Tariq Shikhipar 宣布离职,随后桌面版代理作者 Anthony Morris 也被解雇。Shikhipar…
2026年10月27日AI新闻摘要
今天的人工智能世界展示了技术如何更深入地融入各个行业和地区。Nvidia支持印度初创公司Simplismart,确保伦...
ENGeneral Compute raises $100 million Series A, countering the neocloud disaster narrative
General Compute is betting on inference chips from outside the Nvidia ecosystem.
为什么网络安全需要 AI | Cisco 的 Jeetu Patel
“要保持安全,必须使用 AI,这是先决条件。” 攻击者可以以机器速度行动。防御者需要能同样快速适应的安全控制。Cisco 总裁 Jeetu Patel 解释了为什么 OpenAI 正成为这项工作的核心基础。凭借……能力

