OneShield -- the Next Generation of LLM Guardrails
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_ | 1866916874719068160 |
|---|---|
| author | DeLuca, Chad Gentile, Anna Lisa Asthana, Shubhi Zhang, Bing Chowdhary, Pawan Cheng, Kellen Shbita, Basel Li, Pengyuan Ren, Guang-Jie Gopisetty, Sandeep |
| author_facet | DeLuca, Chad Gentile, Anna Lisa Asthana, Shubhi Zhang, Bing Chowdhary, Pawan Cheng, Kellen Shbita, Basel Li, Pengyuan Ren, Guang-Jie Gopisetty, Sandeep |
| contents | The rise of Large Language Models has created a general excitement about the great potential for a myriad of applications. While LLMs offer many possibilities, questions about safety, privacy, and ethics have emerged, and all the key actors are working to address these issues with protective measures for their own models and standalone solutions. The constantly evolving nature of LLMs makes it extremely challenging to universally shield users against their potential risks, and one-size-fits-all solutions are unfeasible. In this work, we propose OneShield, our stand-alone, model-agnostic and customizable solution to safeguard LLMs. OneShield aims to provide facilities for defining risk factors, expressing and declaring contextual safety and compliance policies, and mitigating LLM risks, with a focus on each specific customer. We describe the implementation of the framework, discuss scalability considerations, and provide usage statistics of OneShield since its initial deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_21170 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OneShield -- the Next Generation of LLM Guardrails DeLuca, Chad Gentile, Anna Lisa Asthana, Shubhi Zhang, Bing Chowdhary, Pawan Cheng, Kellen Shbita, Basel Li, Pengyuan Ren, Guang-Jie Gopisetty, Sandeep Cryptography and Security Artificial Intelligence Computation and Language The rise of Large Language Models has created a general excitement about the great potential for a myriad of applications. While LLMs offer many possibilities, questions about safety, privacy, and ethics have emerged, and all the key actors are working to address these issues with protective measures for their own models and standalone solutions. The constantly evolving nature of LLMs makes it extremely challenging to universally shield users against their potential risks, and one-size-fits-all solutions are unfeasible. In this work, we propose OneShield, our stand-alone, model-agnostic and customizable solution to safeguard LLMs. OneShield aims to provide facilities for defining risk factors, expressing and declaring contextual safety and compliance policies, and mitigating LLM risks, with a focus on each specific customer. We describe the implementation of the framework, discuss scalability considerations, and provide usage statistics of OneShield since its initial deployment. |
| title | OneShield -- the Next Generation of LLM Guardrails |
| topic | Cryptography and Security Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2507.21170 |