# Sugar-Coated Poison: Benign Generation Unlocks LLM Jailbreaking

arXiv: https://arxiv.org/abs/2504.05652 · HTML: https://mlsanity.com/paper/2504.05652/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 27 of its 48 references that are in the map.
- First posted on arXiv 8 Apr 2025.

## Placed in

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

## Builds on (most cited first, 27 of 27)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [Safety Alignment Should Be Made More Than Just a Few Tokens Deep](https://mlsanity.com/paper/2406.05946/) (2024)
- [DeepInception: Hypnotize Large Language Model to Be Jailbreaker](https://mlsanity.com/paper/2311.03191/) (2023)
- [Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision](https://mlsanity.com/paper/2305.03047/) (2023)
- [Recursively Summarizing Books with Human Feedback](https://mlsanity.com/paper/2109.10862/) (2021)
- [A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily](https://mlsanity.com/paper/2311.08268/) (2023)
- [ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs](https://mlsanity.com/paper/2402.11753/) (2024)
- [AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs](https://mlsanity.com/paper/2410.05295/) (2024)
- [COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability](https://mlsanity.com/paper/2402.08679/) (2024)
- [Recipes for Safety in Open-domain Chatbots](https://mlsanity.com/paper/2010.07079/) (2020)
- [Aligning Large Language Models with Human Preferences through Representation Engineering](https://mlsanity.com/paper/2312.15997/) (2023)
- [When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search](https://mlsanity.com/paper/2406.08705/) (2024)
- [LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordination](https://mlsanity.com/paper/2309.11696/) (2023)
- [ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings](https://mlsanity.com/paper/2402.16006/) (2024)
- [PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs](https://mlsanity.com/paper/2406.02886/) (2024)
- [Parameter-Efficient Fine-Tuning of Large Language Models via Deconvolution in Subspace](https://mlsanity.com/paper/2503.01419/) (2025)

## Built on by (most cited first, 6 of 6)

- [MI-PRUN: Optimize Large Language Model Pruning via Mutual Information](https://mlsanity.com/paper/2601.07212/) (2026)
- [Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking](https://mlsanity.com/paper/2602.24009/) (2026)
- [The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation-Triggered Jailbreak in LLMs](https://mlsanity.com/paper/2603.08234/) (2026)
- [BreakFun: Jailbreaking LLMs via Object Instantiation under Simulated Code Execution](https://mlsanity.com/paper/2510.17904/) (2025)
- [DeepSeek Robustness Against Semantic-Character Dual-Space Mutated Prompt Injection](https://mlsanity.com/paper/2604.12548/) (2026)
- [Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution](https://mlsanity.com/paper/2605.13411/) (2026)

## Abstract (arXiv)

With the increasingly deep integration of large language models (LLMs) across diverse domains, the effectiveness of their safety mechanisms is encountering severe challenges. Currently, jailbreak attacks based on prompt engineering have become a major safety threat. However, existing methods primarily rely on black-box manipulation of prompt templates, resulting in poor interpretability and limited generalization. To break through the bottleneck, this study first introduces the concept of Defense Threshold Decay (DTD), revealing the potential safety impact caused by LLMs' benign generation: as benign content generation in LLMs increases, the model's focus on input instructions progressively diminishes. Building on this insight, we propose the Sugar-Coated Poison (SCP) attack paradigm, which uses a "semantic reversal" strategy to craft benign inputs that are opposite in meaning to malicious intent. This strategy induces the models to generate extensive benign content, thereby enabling adversarial reasoning to bypass safety mechanisms. Experiments show that SCP outperforms existing baselines. Remarkably, it achieves an average attack success rate of 87.23% across six LLMs. For defense, we propose Part-of-Speech Defense (POSD), leveraging verb-noun dependencies for syntactic analysis to enhance safety of LLMs while preserving their generalization ability.