Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917253148049408 |
|---|---|
| author | Chen, Sizhe Zharmagambetov, Arman Wagner, David Guo, Chuan |
| author_facet | Chen, Sizhe Zharmagambetov, Arman Wagner, David Guo, Chuan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_02735 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks Chen, Sizhe Zharmagambetov, Arman Wagner, David Guo, Chuan Cryptography and Security Artificial Intelligence 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. |
| title | Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2507.02735 |