# Dynamic Guided and Domain Applicable Safeguards for Enhanced Security in Large Language Models

arXiv: https://arxiv.org/abs/2410.17922 · HTML: https://mlsanity.com/paper/2410.17922/

## 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 23 Oct 2024.

## Placed in

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

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

- [Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models](https://mlsanity.com/paper/2504.19373/) (2025)
- [Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection](https://mlsanity.com/paper/2510.01270/) (2025)
- [sudoLLM: On Multi-role Alignment of Language Models](https://mlsanity.com/paper/2505.14607/) (2025)
- [MENTOR: A Metacognition-Driven Self-Evolution Framework for Uncovering and Mitigating Implicit Domain Risks in LLMs](https://mlsanity.com/paper/2511.07107/) (2025)
- [Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models](https://mlsanity.com/paper/2604.01444/) (2026)

## Abstract (arXiv)

With the extensive deployment of Large Language Models (LLMs), ensuring their safety has become increasingly critical. However, existing defense methods often struggle with two key issues: (i) inadequate defense capabilities, particularly in domain-specific scenarios like chemistry, where a lack of specialized knowledge can lead to the generation of harmful responses to malicious queries. (ii) over-defensiveness, which compromises the general utility and responsiveness of LLMs. To mitigate these issues, we introduce a multi-agents-based defense framework, Guide for Defense (G4D), which leverages accurate external information to provide an unbiased summary of user intentions and analytically grounded safety response guidance. Extensive experiments on popular jailbreak attacks and benign datasets show that our G4D can enhance LLM's robustness against jailbreak attacks on general and domain-specific scenarios without compromising the model's general functionality.