# Don't Say No: Jailbreaking LLM by Suppressing Refusal

arXiv: https://arxiv.org/abs/2404.16369 · HTML: https://mlsanity.com/paper/2404.16369/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 39 of its 69 references that are in the map.
- First posted on arXiv 25 Apr 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Safety alignment and jailbreak attacks](https://mlsanity.com/alignment/safety-alignment-and-jailbreak-attacks/)
- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 30 of 39)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [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)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [Delving into Transferable Adversarial Examples and Black-box Attacks](https://mlsanity.com/paper/1611.02770/) (2016)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks](https://mlsanity.com/paper/2404.02151/) (2024)
- [SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2310.03684/) (2023)
- [Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation](https://mlsanity.com/paper/2310.06987/) (2023)
- [FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts](https://mlsanity.com/paper/2311.05608/) (2023)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery](https://mlsanity.com/paper/2302.03668/) (2023)
- [Are aligned neural networks adversarially aligned?](https://mlsanity.com/paper/2306.15447/) (2023)
- [MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots](https://mlsanity.com/paper/2307.08715/) (2023)
- [AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs](https://mlsanity.com/paper/2404.07921/) (2024)

## Built on by (most cited first, 30 of 56)

- [Jailbreak Attacks and Defenses Against Large Language Models: A Survey](https://mlsanity.com/paper/2407.04295/) (2024)
- [Steering Language Model Refusal with Sparse Autoencoders](https://mlsanity.com/paper/2411.11296/) (2024)
- [SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types](https://mlsanity.com/paper/2410.21965/) (2024)
- [Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment](https://mlsanity.com/paper/2411.18688/) (2024)
- [Who is Introducing the Failure? Automatically Attributing Failures of Multi-Agent Systems via Spectrum Analysis](https://mlsanity.com/paper/2509.13782/) (2025)
- [No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks](https://mlsanity.com/paper/2405.16229/) (2024)
- [SaRO: Enhancing LLM Safety through Reasoning-based Alignment](https://mlsanity.com/paper/2504.09420/) (2025)
- [AdvPrefix: An Objective for Nuanced LLM Jailbreaks](https://mlsanity.com/paper/2412.10321/) (2024)
- [Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture](https://mlsanity.com/paper/2407.07342/) (2024)
- [Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment](https://mlsanity.com/paper/2405.13068/) (2024)
- [Adversarial Attacks on Large Language Models Using Regularized Relaxation](https://mlsanity.com/paper/2410.19160/) (2024)
- [Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training](https://mlsanity.com/paper/2502.11455/) (2025)
- [Jailbreaking as a Reward Misspecification Problem](https://mlsanity.com/paper/2406.14393/) (2024)
- [HYBRIDMIND: Meta Selection of Natural Language and Symbolic Language for Enhanced LLM Reasoning](https://mlsanity.com/paper/2409.19381/) (2024)
- [TAI3: Testing Agent Integrity in Interpreting User Intent](https://mlsanity.com/paper/2506.07524/) (2025)
- [Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs](https://mlsanity.com/paper/2602.08621/) (2026)
- [POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization](https://mlsanity.com/paper/2410.12999/) (2024)
- [MetaDefense: Defending Finetuning-based Jailbreak Attack Before and During Generation](https://mlsanity.com/paper/2510.07835/) (2025)
- [LLM Content Moderation and User Satisfaction: Evidence from Response Refusals in Chatbot Arena](https://mlsanity.com/paper/2501.03266/) (2025)
- [TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice](https://mlsanity.com/paper/2502.18504/) (2025)
- [CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs](https://mlsanity.com/paper/2510.09871/) (2025)
- [Large Language Model Sourcing: A Survey](https://mlsanity.com/paper/2510.10161/) (2025)
- [SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses](https://mlsanity.com/paper/2510.15476/) (2025)
- [Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference](https://mlsanity.com/paper/2407.00075/) (2024)
- [LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds](https://mlsanity.com/paper/2412.05232/) (2024)
- [Breaking Audio Large Language Models by Attacking Only the Encoder: A Universal Targeted Latent-Space Audio Attack](https://mlsanity.com/paper/2512.23881/) (2025)
- [textitMMJ-Bench: A Comprehensive Study on Jailbreak Attacks and Defenses for Multimodal Large Language Models](https://mlsanity.com/paper/2408.08464/) (2024)
- [Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs](https://mlsanity.com/paper/2501.16534/) (2025)
- [Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures](https://mlsanity.com/paper/2506.07402/) (2025)
- [NonTextual Target Attack](https://mlsanity.com/paper/2510.02999/) (2025)

## Abstract (arXiv)

Ensuring the safety alignment of Large Language Models (LLMs) is critical for generating responses consistent with human values. However, LLMs remain vulnerable to jailbreaking attacks, where carefully crafted prompts manipulate them into producing toxic content. One category of such attacks reformulates the task as an optimization problem, aiming to elicit affirmative responses from the LLM. However, these methods heavily rely on predefined objectionable behaviors, limiting their effectiveness and adaptability to diverse harmful queries. In this study, we first identify why the vanilla target loss is suboptimal and then propose enhancements to the loss objective. We introduce DSN (Don't Say No) attack, which combines a cosine decay schedule method with refusal suppression to achieve higher success rates. Extensive experiments demonstrate that DSN outperforms baseline attacks and achieves state-of-the-art attack success rates (ASR). DSN also shows strong universality and transferability to unseen datasets and black-box models.