Anthropic 扩展网络验证计划，推出三级安全访问层级
原标题：Expanding the Cyber Verification Program
AI 摘要
Anthropic 宣布扩展其 Cyber Verification Program（CVP），将原有的 Project Glasswing 与 CVP 整合为统一计划，并设立 Defense Access、Red Team Access、Specialized Access 三个访问层级，向合格安全专业人员提供更少拦截分类器的高级网络能力。各层级均包含 Claude Opus 5.5、Claude Sonnet 5.5、Claude Mythos 5.1 等模型，并设有不同验证要求与安全控制。Anthropic 还使用 CyScenarioBench 评估各层级防护效果，显示无 CVP 访问时任务全部被拦截，Defense 层级 50 次试验中 46 次被拦截，Red Team 层级无拦截且成功完成 34 次任务。
正文节选
Expanding the Cyber Verification Program We’re launching a new, expanded version of our Cyber Verification Program (CVP), which makes advanced cyber capabilities and reduced blocking classifiers available to qualifying security professionals. The program now consists of three access tiers, which allow security teams to apply for the level of access that best suits their work. Each tier includes access to our most capable models, including Claude Opus 5.5, Claude Sonnet 5.5, Claude Mythos 5.1, an