mlsanityData to 7 Oct 2026

Jailbreaking with Universal Multi-Prompts

arXiv 2502.01154 ↗First posted 3 Feb 2025cs.CL cs.AI cs.CRcited by 2

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

Large language models (LLMs) have seen rapid development in recent years, revolutionizing various applications and significantly enhancing convenience and productivity. However, alongside their impressive capabilities, ethical concerns and new types of attacks, such as jailbreaking, have emerged. While most prompting techniques focus on optimizing adversarial inputs for individual cases, resulting in higher computational costs when dealing with large datasets. Less research has addressed the more general setting of training a universal attacker that can transfer to unseen tasks. In this paper, we introduce JUMP, a prompt-based method designed to jailbreak LLMs using universal multi-prompts. We also adapt our approach for defense, which we term DUMP. Experimental results demonstrate that our method for optimizing universal multi-prompts outperforms existing techniques.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 27 of its 39 references that are in the map. First posted on arXiv 3 Feb 2025.

Builds on

27 of 39 references.

Closest ancestors · 13

Same direction, newest first

  1. 2024DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak23 Dec
  2. 2024GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs21 Nov
  3. 2024Jailbreaking as a Reward Misspecification Problem20 Jun
  4. 2024Fast Adversarial Attacks on Language Models In One GPU Minute23 Feb
  5. 2024Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks30 Jan
  6. 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automatically4 Dec
  7. 2023Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation6 Nov
  8. 2023Jailbreaking Black Box Large Language Models in Twenty Queries12 Oct
  9. 2023Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations10 Oct
  10. 2023SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks5 Oct
  11. 2023GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts19 Sep
  12. 2023Detecting Language Model Attacks with Perplexity27 Aug
1 more
  1. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul

Other references · 14

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  8. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,124
  9. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 663
  10. 2020BERT-ATTACK: Adversarial Attack Against BERT Using BERTcited by 488
  11. 2018Generating Natural Language Adversarial Examplescited by 422
  12. 2020AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Promptscited by 246
2 more
  1. 2021Gradient-based Adversarial Attacks against Text Transformerscited by 233
  2. 2021Language Model Evaluation Beyond Perplexitycited by 77

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Multilingual and Multi-Accent Jailbreaking of Audio LLMscited by 25
  2. 2025ForgeDAN: An Evolutionary Framework for Jailbreaking Aligned Large Language Modelscited by 0