域名伪装注入攻击在多智能体大语言模型系统中规避检测
Domain-Camouflaged Injection Attacks Evade Detection in Multi-Agent LLM Systems

原始链接: https://arxiv.org/abs/2605.22001

arXivLabs 是一个允许合作者直接在我们的网站上开发并分享 arXiv 新功能的框架。与 arXivLabs 合作的个人和组织都认同并接受我们对开放、社区、卓越和用户数据隐私的重视。arXiv 始终坚持这些价值观,并仅与遵循这些价值观的合作伙伴进行合作。如果您有能为 arXiv 社区创造价值的项目构想,请了解更多关于 arXivLabs 的信息。

Sorry.
相关文章

原文

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

联系我们 contact @ memedata.com