# Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning

arXiv: https://arxiv.org/abs/2501.19180 · HTML: https://mlsanity.com/paper/2501.19180/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 28 of its 64 references that are in the map.
- First posted on arXiv 31 Jan 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 28 of 28)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024)
- [A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily](https://mlsanity.com/paper/2311.08268/) (2023)
- [SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal](https://mlsanity.com/paper/2406.14598/) (2024)
- [Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications](https://mlsanity.com/paper/2402.05162/) (2024)
- [Simulating Classroom Education with LLM-Empowered Agents](https://mlsanity.com/paper/2406.19226/) (2024)
- [What is in Your Safe Data? Identifying Benign Data that Breaks Safety](https://mlsanity.com/paper/2404.01099/) (2024)
- [LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts](https://mlsanity.com/paper/2410.10700/) (2024)
- [Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue](https://mlsanity.com/paper/2402.17262/) (2024)
- [Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons](https://mlsanity.com/paper/2406.14144/) (2024)
- [MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue](https://mlsanity.com/paper/2411.03814/) (2024)
- [Learning and Forgetting Unsafe Examples in Large Language Models](https://mlsanity.com/paper/2312.12736/) (2023)
- [LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language](https://mlsanity.com/paper/2501.14073/) (2025)
- [Multi-round jailbreak attack on large language models](https://mlsanity.com/paper/2410.11533/) (2024)

## Built on by (most cited first, 11 of 11)

- [A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models](https://mlsanity.com/paper/2509.03871/) (2025)
- [How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study](https://mlsanity.com/paper/2505.15404/) (2025)
- [AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning](https://mlsanity.com/paper/2507.14987/) (2025)
- [Strong but Brittle: Simple Attacks Subvert Reasoning-based Safety Guardrails](https://mlsanity.com/paper/2510.11570/) (2025)
- [CoTGuard: Using Chain-of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systems](https://mlsanity.com/paper/2505.19405/) (2025)
- [RvB: Automating AI System Hardening via Iterative Red-Blue Games](https://mlsanity.com/paper/2601.19726/) (2026)
- [Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward](https://mlsanity.com/paper/2604.09748/) (2026)
- [SoK: Robustness in Large Language Models against Jailbreak Attacks](https://mlsanity.com/paper/2605.05058/) (2026)
- [Why Agents Compromise Safety Under Pressure](https://mlsanity.com/paper/2603.14975/) (2026)
- [Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications](https://mlsanity.com/paper/2605.24883/) (2026)
- [Addressing Over-Refusal in LLMs with Competing Rewards](https://mlsanity.com/paper/2606.31748/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are vital for a wide range of applications yet remain susceptible to jailbreak threats, which could lead to the generation of inappropriate responses. Conventional defenses, such as refusal and adversarial training, often fail to cover corner cases or rare domains, leaving LLMs still vulnerable to more sophisticated attacks. We propose a novel defense strategy, Safety Chain-of-Thought (SCoT), which harnesses the enhanced textitreasoning capabilities of LLMs for proactive assessment of harmful inputs, rather than simply blocking them. SCoT augments any refusal training datasets to critically analyze the intent behind each request before generating answers. By employing proactive reasoning, SCoT enhances the generalization of LLMs across varied harmful queries and scenarios not covered in the safety alignment corpus. Additionally, it generates detailed refusals specifying the rules violated. Comparative evaluations show that SCoT significantly surpasses existing defenses, reducing vulnerability to out-of-distribution issues and adversarial manipulations while maintaining strong general capabilities.