行业动态
x.com ·
@GaryMarcus
Gary Marcus 提醒：用 AI 做网络防御可能反而引入新攻击面
Gary Marcus 引用 HeidyKhlaaf 的攻击演示指出，将 AI 用于网络防御会引入未缓解的攻击向量，可能抵消甚至恶化原本追求的防御优势；他同时提到 OpenAI 使用防御性 AI 仍遭入侵，说明防御性 AI 并非万能。相关技术细节需查看原帖线程，OpenAI 被黑说法未在正文中给出证据。
AI推荐理由 Gary Marcus 转述 HeidyKhlaaf 的攻击演示，指出用 AI 做网络防御可能引入未缓解的攻击面，反而削弱甚至恶化防御优势，并提到 OpenAI 使用防御性 AI 仍遭入侵。这是对“更多 AI 即更好防御”这一流行论调的具体反例，涉及 AI 安全与攻防对抗的实际局限；但正文仅为转述与引用，未给出技术细节，OpenAI 被黑一事也未提供证据，需保留不确定性。
62
浏览 725
点赞 4
评论 2
转发 1
正文
caution: [@DavidSacks](https://x.com/DavidSacks) is getting loads of traffic saying the best defense against cyberattacks is more AI.
but sometimes that actually makes things worse, this thread/demonstration from [@HeidyKhlaaf](https://x.com/HeidyKhlaaf) shows. (scroll to the top of her thread for the technical details.)
also, defensive AI isn’t magic. ask OpenAI, which used it and still got hacked.
Dr Heidy Khlaaf (هايدي خلاف)@HeidyKhlaaf
Our attack demonstrates how the use of AI for cyber defense introduces unmitigated attack vectors that may defeat, if not worsen, any defensive advantages that were sought to combat (alleged) offensive AI capabilities.
[🔗 View Quoted Tweet](https://x.com/HeidyKhlaaf/status/2074840962958798853)