Prompt injection attacks, where untrusted data contains an injected prompt to manipulate the system, have been listed as the top security threat to LLM-integrated applications. Model-level prompt injection defenses have shown strong effectiveness, but the strongest defenses are proprietary. Open-source secure models are needed by the AI security community so that co-development of attacks and defenses through open research can drive scientific progress in mitigating prompt injection attacks. To this end, we develop Meta SecAlign, the first fully open-source LLM with built-in model-level defense that achieves commercial-grade performance and is powerful enough for complex agentic tasks. We provide complete details of our training recipe. We perform the most comprehensive evaluation to date on 9 utility benchmarks (measuring general knowledge, instruction following, and agentic workflows) and 7 security benchmarks. Results show that Meta SecAlign, despite being trained only on generic instruction-tuning samples, surprisingly confers security in unseen downstream tasks, including tool-calling and web-navigation, in addition to general instruction-following. Our best model -- Meta-SecAlign-70B -- establishes a new frontier of utility-security trade-off for open-source LLMs, and is more secure than several flagship proprietary models with prompt injection defense. Below are links for the code (https://github.com/facebookresearch/Meta_SecAlign), Meta-SecAlign-70B (https://huggingface.co/facebook/Meta-SecAlign-70B), and Meta-SecAlign-8B (https://huggingface.co/facebook/Meta-SecAlign-8B) models.

翻译：提示注入攻击，即不受信任的数据包含被注入的提示以操纵系统，已被列为LLM集成应用的首要安全威胁。模型级提示注入防御已显示出强大的有效性，但最强的防御方案是专有的。AI安全社区需要开源的安全模型，以便通过开放研究共同开发攻击和防御，从而推动缓解提示注入攻击的科学研究进展。为此，我们开发了Meta SecAlign，这是首个完全开源、内置模型级防御的大语言模型，其性能达到商业级水平，且足够强大以处理复杂的智能体任务。我们提供了完整的训练方案细节。我们进行了迄今为止最全面的评估，涵盖9个效用基准（衡量通用知识、指令遵循和智能体工作流）和7个安全基准。结果表明，尽管Meta SecAlign仅使用通用指令微调样本进行训练，却出人意料地在未见的下游任务（包括工具调用和网络导航）以及通用指令遵循中赋予了安全性。我们的最佳模型——Meta-SecAlign-70B——为开源大语言模型在效用与安全权衡方面树立了新的前沿，其安全性甚至超过多个具备提示注入防御功能的旗舰专有模型。以下是代码（https://github.com/facebookresearch/Meta_SecAlign）、Meta-SecAlign-70B（https://huggingface.co/facebook/Meta-SecAlign-70B）和Meta-SecAlign-8B（https://huggingface.co/facebook/Meta-SecAlign-8B）模型的链接。