Anthropic: Mythos has been able to transform publicly known vulnerabilities into executable exploits

BlockBeats News, June 9th, Anthropic's latest test results show that its AI model Mythos successfully exploited 18 of the 21 recently disclosed Windows kernel vulnerabilities, with a success rate of approximately 86%. Mythos is able to automatically generate runnable network attack exploits based on publicly known vulnerability information, with an average cost of around $2,000 per successful exploit code.

Anthropic stated that Mythos has demonstrated the capability to translate public vulnerabilities into effective attack tools. This research highlights the dual-purpose nature of advanced AI models in the field of cybersecurity, raising further concerns in the industry about the boundaries of AI capabilities and security governance.

---------------------------------
Click the original article link below to join the BlockBeats · Feishu AI News Channel and receive real-time monitoring of global AI trends and news 24/7.