# TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts

arXiv: https://arxiv.org/abs/2506.07596 · HTML: https://mlsanity.com/paper/2506.07596/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 41 of its 60 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Placed in

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

## Builds on (most cited first, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [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)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [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)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [DeepSeek LLM: Scaling Open-Source Language Models with Longtermism](https://mlsanity.com/paper/2401.02954/) (2024)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (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)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)
- [Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks](https://mlsanity.com/paper/2404.02151/) (2024)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)

## Built on by (most cited first, 19 of 19)

- [MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks](https://mlsanity.com/paper/2602.09222/) (2026)
- [GateBreaker: Gate-Guided Attacks on Mixture-of-Expert LLMs](https://mlsanity.com/paper/2512.21008/) (2025)
- [GRP-Obliteration: Unaligning LLMs With a Single Unlabeled Prompt](https://mlsanity.com/paper/2602.06258/) (2026)
- [SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses](https://mlsanity.com/paper/2510.15476/) (2025)
- [QuadSentinel: Sequent Safety for Machine-Checkable Control in Multi-agent Systems](https://mlsanity.com/paper/2512.16279/) (2025)
- [Large Language Lobotomy: Jailbreaking Mixture-of-Experts via Expert Silencing](https://mlsanity.com/paper/2602.08741/) (2026)
- [DynaTrust: Defending Multi-Agent Systems Against Sleeper Agents via Dynamic Trust Graphs](https://mlsanity.com/paper/2603.15661/) (2026)
- [Misrouter: Exploiting Routing Mechanisms for Input-Only Attacks on Mixture-of-Experts LLMs](https://mlsanity.com/paper/2605.04446/) (2026)
- [NeST: Neuron Selective Tuning for LLM Safety](https://mlsanity.com/paper/2602.16835/) (2026)
- [Can LLMs Threaten Human Survival? Benchmarking Potential Existential Threats from LLMs via Prefix Completion](https://mlsanity.com/paper/2511.19171/) (2025)
- [SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks](https://mlsanity.com/paper/2608.01117/) (2026)
- [RoguePrompt: Dual-Layer Ciphering for Self-Reconstruction to Circumvent LLM Moderation](https://mlsanity.com/paper/2511.18790/) (2025)
- [A Causal Perspective for Enhancing Jailbreak Attack and Defense](https://mlsanity.com/paper/2602.04893/) (2026)
- [The Art of the Jailbreak: Formulating Jailbreak Attacks for LLM Security Beyond Binary Scoring](https://mlsanity.com/paper/2605.09225/) (2026)
- [Mask2Shield: Strengthening LLM Safety against Neuron-Pruning Attacks](https://mlsanity.com/paper/2607.23015/) (2026)
- [RoguePrompt: Dual-Layer Encoding for Self-Reconstruction to Circumvent LLM Moderation](https://mlsanity.com/paper/2607.27373/) (2026)
- [Decided Upstream, Written Late: Locating and Pricing the Cross-Lingual Refusal Circuit of a Multilingual MoE](https://mlsanity.com/paper/2608.08032/) (2026)
- [Localizing Safety Alignment: MLP Layers and Mid-Network Blocks Encode Refusal Behavior in Large Language Models](https://mlsanity.com/paper/2608.11583/) (2026)
- [Fool's Gold: Defensive Deception Against Safety-Removal Attacks on Open-Weight Models](https://mlsanity.com/paper/2608.17202/) (2026)

## Abstract (arXiv)

Machine learning is advancing rapidly, with applications bringing notable benefits, such as improvements in translation and code generation. Models like ChatGPT, powered by Large Language Models (LLMs), are increasingly integrated into daily life. However, alongside these benefits, LLMs also introduce social risks. Malicious users can exploit LLMs by submitting harmful prompts, such as requesting instructions for illegal activities. To mitigate this, models often include a security mechanism that automatically rejects such harmful prompts. However, they can be bypassed through LLM jailbreaks. Current jailbreaks often require significant manual effort, high computational costs, or result in excessive model modifications that may degrade regular utility. We introduce TwinBreak, an innovative safety alignment removal method. Building on the idea that the safety mechanism operates like an embedded backdoor, TwinBreak identifies and prunes parameters responsible for this functionality. By focusing on the most relevant model layers, TwinBreak performs fine-grained analysis of parameters essential to model utility and safety. TwinBreak is the first method to analyze intermediate outputs from prompts with high structural and content similarity to isolate safety parameters. We present the TwinPrompt dataset containing 100 such twin prompts. Experiments confirm TwinBreak's effectiveness, achieving 89% to 98% success rates with minimal computational requirements across 16 LLMs from five vendors.