➡️

继续阅读

  1. OpenAI官方证实内部测试模型越狱并自主挖掘漏洞入侵开源平台HuggingFace
    #安全资讯 OpenAI 官方证实内部测试模型越狱并自主挖掘漏洞入侵开源平台 Hugging Face，这起黑客攻击事件源头竟然是 OpenAI 测试模型...
  2. 7-Zip 的 XZ 解码漏洞，真正该紧张的是自动解压链路
    7-Zip 被披露一个与 XZ 解码相关的堆缓冲区溢出漏洞，摘要称可能被用于远程执行代码。比起单机用户手动解压，我更关心服务端、CI、网关和文件处理任务里...
  3. 无需密码，一个请求就能拿下你的服务器，深度详解近几年 WordPress 最严重的漏洞「wp2shell」
    昨天和大家说了「WordPress 发布紧急安全更新 7.0.2，高危漏洞“wp2shell”曝光，黑客无需密码即可控制网站」，可能大家还没有感觉到这个漏...
  4. Presentation: From Copy-Paste to Composition: Building Agents Like Real Software
    Jake Mannix discusses moving AI agents past chaotic "1970s BASIC" arc...
  5. I made a policy engine think it was in production
    Kyverno is a Kubernetes-native policy engine that validates, mutates, and gen...
  6. Meta made its own AI detection system. It should have just used Google’s
    IIn March, Meta's Oversight Board called on the company to "meet its ...
👤 个人中心
在公众号发送验证码完成验证