# Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs

arXiv: https://arxiv.org/abs/2501.02018 · HTML: https://mlsanity.com/paper/2501.02018/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- First posted on arXiv 2 Jan 2025.

## Placed in

- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Built on by (most cited first, 5 of 5)

- [Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks](https://mlsanity.com/paper/2503.00187/) (2025)
- [On Almost Surely Safe Alignment of Large Language Models at Inference-Time](https://mlsanity.com/paper/2502.01208/) (2025)
- [The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems](https://mlsanity.com/paper/2507.02097/) (2025)
- [CARE: Decoding Time Safety Alignment via Rollback and Introspection Intervention](https://mlsanity.com/paper/2509.06982/) (2025)
- [CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment](https://mlsanity.com/paper/2608.21278/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have been shown to be susceptible to jailbreak attacks, or adversarial attacks used to illicit high risk behavior from a model. Jailbreaks have been exploited by cybercriminals and blackhat actors to cause significant harm, highlighting the critical need to safeguard widely-deployed models. Safeguarding approaches, which include fine-tuning models or having LLMs "self-reflect", may lengthen the inference time of a model, incur a computational penalty, reduce the semantic fluency of an output, and restrict ``normal'' model behavior. Importantly, these Safety-Performance Trade-offs (SPTs) remain an understudied area. In this work, we introduce a novel safeguard, called SafeNudge, that combines Controlled Text Generation with "nudging", or using text interventions to change the behavior of a model. SafeNudge triggers during text-generation while a jailbreak attack is being executed, and can reduce successful jailbreak attempts by 30% by guiding the LLM towards a safe responses. It adds minimal latency to inference and has a negligible impact on the semantic fluency of outputs. Further, we allow for tunable SPTs. SafeNudge is open-source and available through https://pypi.org/, and is compatible with models loaded with the Hugging Face "transformers" library.