How AI guardrails are impeding the work of offensive cybersecurity researchers
中文摘要
OpenAI和Anthropic的AI安全防护机制正阻碍攻击性网络安全研究人员发现系统漏洞及开发利用工具的工作。
English Summary
AI guardrails from OpenAI and Anthropic are hindering offensive cybersecurity researchers from discovering vulnerabilities and developing necessary exploit tools.
Original Excerpt
We spoke with several cybersecurity researchers, who look for unknown vulnerabilities and develop tools to exploit them, about how OpenAI’s and Anthropic’s guardrails affect their work.