Anthropic 与 Gray Swan 举办提示注入红队竞赛
Over the last few years, we have made significant progress on prompt injection for Claude models. As agents do more, it is increasingly urgent that we solve it
Boris Cherny 表示，过去几年 Claude 模型在提示注入防护上取得显著进展，但随着智能体承担更多任务，整个行业解决这一问题的紧迫性在上升。他宣布与 Gray Swan 合作举办相关竞赛，并期待看到参赛者的发现。Gray Swan 称该竞赛与 Anthropic、Meta、Google DeepMind、Reflection 等前沿实验室赞助方合作，奖金 30 万美元，主题为间接提示注入。
推荐理由
AI 评分 58
Anthropic 与 Gray Swan 联合举办间接提示注入红队竞赛，读者可了解智能体安全当前面临的行业级挑战。
主题
查看原帖Is prompt injection solved? Here’s $300,000 to find out. In partnership with @AnthropicAI, @Meta, @GoogleDeepMind, @Reflection_ai and our other frontier lab sponsors, @GraySwanAI is excited to announce the largest and most realistic AI red teaming challenge to date. Indirect Prompt Injection: Black ⚫
正文
当前显示原文，中文全文译文尚未就绪。
Over the last few years, we have made significant progress on prompt injection for Claude models. As agents do more, it is increasingly urgent that we solve it across the industry.
Really excited to partner with Gray Swan to host this competition. Can’t wait to see what you find!