# OneShield -- the Next Generation of LLM Guardrails

arXiv: https://arxiv.org/abs/2507.21170 · HTML: https://mlsanity.com/paper/2507.21170/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 25 Jul 2025.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 8 of 8)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails](https://mlsanity.com/paper/2310.10501/) (2023)
- [Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction](https://mlsanity.com/paper/2210.05791/) (2022)
- [Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey](https://mlsanity.com/paper/2402.09283/) (2024)
- [Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation](https://mlsanity.com/paper/2406.20053/) (2024)
- [LAB: Large-Scale Alignment for ChatBots](https://mlsanity.com/paper/2403.01081/) (2024)
- [Assessing Language Model Deployment with Risk Cards](https://mlsanity.com/paper/2303.18190/) (2023)

## Built on by (most cited first, 3 of 3)

- [AgentGuardian: Learning Access Control Policies to Govern AI Agent Behavior](https://mlsanity.com/paper/2601.10440/) (2026)
- [A Lightweight Explainable Guardrail for Prompt Safety](https://mlsanity.com/paper/2602.15853/) (2026)
- [Backprompting: Leveraging Synthetic Production Data for Health Advice Guardrails](https://mlsanity.com/paper/2508.18384/) (2025)

## Abstract (arXiv)

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.