mlsanityData to 7 Oct 2026

Iterative Prompting with Persuasion Skills in Jailbreaking Large Language Models

arXiv 2503.20320 ↗First posted 26 Mar 2025cs.CL cs.AI cs.ETcited by 2

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

Large language models (LLMs) are designed to align with human values in their responses. This study exploits LLMs with an iterative prompting technique where each prompt is systematically modified and refined across multiple iterations to enhance its effectiveness in jailbreaking attacks progressively. This technique involves analyzing the response patterns of LLMs, including GPT-3.5, GPT-4, LLaMa2, Vicuna, and ChatGLM, allowing us to adjust and optimize prompts to evade the LLMs' ethical and security constraints. Persuasion strategies enhance prompt effectiveness while maintaining consistency with malicious intent. Our results show that the attack success rates (ASR) increase as the attacking prompts become more refined with the highest ASR of 90% for GPT4 and ChatGLM and the lowest ASR of 68% for LLaMa2. Our technique outperforms baseline techniques (PAIR and PAP) in ASR and shows comparable performance with GCG and ArtPrompt.

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 12 of its 12 references that are in the map. First posted on arXiv 26 Mar 2025.

Builds on

12 of 12 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Models17 Jan
  2. 2024How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs12 Jan
  3. 2023Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation6 Nov
  4. 2023Jailbreaking Black Box Large Language Models in Twenty Queries12 Oct
  5. 2023GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts19 Sep
  6. 2023"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models7 Aug
  7. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul
  8. 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study23 May

Other references · 4

  1. 2024ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMscited by 197
  2. 2024Automatic and Universal Prompt Injection Attacks against Large Language Modelscited by 112
  3. 2023Evil Geniuses: Delving into the Safety of LLM-based Agentscited by 103
  4. 2023Guiding Large Language Models via Directional Stimulus Promptingcited by 94

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Your Mailbox Is Mine: Prompt Injection Attacks Against Real-World LLM Email Agentscited by 1
  2. 2025AdversariaL attacK sAfety aLIgnment(ALKALI): Safeguarding LLMs through GRACE: Geometric Representation-Aware Contrastive Enhancement- Introducing Adversarial Vulnerability Quality Index (AVQI)cited by 0