We're publishing our most detailed threat intelligence report to date.
We're publishing our most detailed threat intelligence report to date. It covers how people tried to misuse Claude—for cyberattacks, influence operations, surv…
很对,攻击者早就通过模型越狱/蒸馏训练/破解等方式拥有更强的模型工程,黑灰产业链这方面更是成熟,而还是有大量流行的项目在大模型安全应用上是被限制的,这直接导致了攻防不对称,也就是大家看到的当前一堆安全问题:每天醒来不是又出现 0day、供应链攻击,就是这个被盗那个被黑。🌚
简注
很对,攻击者早就通过模型越狱/蒸馏训练/破解等方式拥有更强的模型工程,黑灰产业链这方面更是成熟,而还是有大量流行的项目在大模型安全应用上是被限制的,这直接导致了攻防不对称,也就是大家看到的当前一堆安全问题:每天醒来不是又出现 0day、供应链攻击,就是这个被盗那个被黑。🌚
优先按共同标签匹配,其次按类型。
We're publishing our most detailed threat intelligence report to date. It covers how people tried to misuse Claude—for cyberattacks, influence operations, surv…
I resigned from Anthropic today. I spent the last three years doing pretraining research at both OpenAI and Anthropic. Neither company is acting responsibly. T…
发现@bot
Introducing Grok Bot, now in early beta. Bots are AI teammates that do real work for you. They sign in to your tools, use them just like you do, and come back…