mlsanityData to 14 Oct 2026

Enhancing Jailbreak Attacks on LLMs via Persona Prompts

arXiv 2507.22171 ↗First posted 28 Jul 2025cs.CR cs.AIcited by 11

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

Jailbreak attacks aim to exploit large language models (LLMs) by inducing them to generate harmful content, thereby revealing their vulnerabilities. Understanding and addressing these attacks is crucial for advancing the field of LLM safety. Previous jailbreak approaches have mainly focused on direct manipulations of harmful intent, with limited attention to the impact of persona prompts. In this study, we systematically explore the efficacy of persona prompts in compromising LLM defenses. We propose a genetic algorithm-based method that automatically crafts persona prompts to bypass LLM's safety mechanisms. Our experiments reveal that: (1) our evolved persona prompts reduce refusal rates by 50-70% across multiple LLMs, and (2) these prompts demonstrate synergistic effects when combined with existing attack methods, increasing success rates by 10-20%. Our code and data are available at https://github.com/CjangCjengh/Generic_Persona.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 26 of its 33 references that are in the map. First posted on arXiv 28 Jul 2025.

Builds on

26 of 33 references.

Closest ancestors · 13

Same direction, newest first

  1. 2024Virtual Context: Enhancing Jailbreak Attacks with Special Token Injection28 Jun
  2. 2024Jailbreaking LLMs with Arabic Transliteration and Arabizi26 Jun
  3. 2024Distract Large Language Models for Automatic Jailbreak Attack13 Mar
  4. 2024ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings25 Feb
  5. 2024How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs12 Jan
  6. 2023Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization15 Nov
  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. 2023AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models3 Oct
  10. 2023GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts19 Sep
  11. 2023GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher12 Aug
  12. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul
1 more
  1. 2023PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts7 Jun

Other references · 13

  1. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 222
  2. 2024ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMscited by 216
  3. 2024Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaborationcited by 189
  4. 2023InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviewscited by 179
  5. 2023RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Modelscited by 175
  6. 2024Quantifying the Persona Effect in LLM Simulationscited by 169
  7. 2024MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Makingcited by 163
  8. 2024FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Makingcited by 113
  9. 2022Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLPcited by 102
  10. 2025Principled Data Selection for Alignment: The Hidden Risks of Difficult Examplescited by 37
  11. 2024The Better Angels of Machine Personality: How Personality Relates to LLM Safetycited by 21
  12. 2025NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Predictioncited by 20
1 more
  1. 2023P5: Plug-and-Play Persona Prompting for Personalized Response Selectioncited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 11.

11 papers.

  1. 2026Who Endorsed It? Measuring Authority Bias Across Expertise Levels in Language Modelscited by 8
  2. 2026ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessionscited by 5
  3. 2026Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMscited by 1
  4. 2026A Theoretical Game of Attacks via Compositional Skillscited by 1
  5. 2026Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignmentcited by 1
  6. 2026Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMscited by 0
  7. 2026Same Model, Different Weakness: How Language and Modality Reshape the Jailbreak Attack Surface in Frontier MLLMscited by 0
  8. 2026EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigationcited by 0
  9. 2026DeflectBench: A Benchmark for Evaluating Rhetorical Fallacy Generation in LLMscited by 0
  10. 2026Reach Into The CHOIR: Free-List Elicitation Uncovers Distinct Model Voices in LLM Ensemblescited by 0
  11. 2026Extracting Persona Subspaces Through Iterative Nullspace Projection For Modulationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models
  2. 2023Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks
  3. 2024Characterizing and Evaluating the Reliability of LLMs against Jailbreak Attacks
  4. 2025You Can't Eat Your Cake and Have It Too: The Performance Degradation of LLMs with Jailbreak Defense
  5. 2024A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models
  6. 2024Intention Analysis Makes LLMs A Good Jailbreak Defender
  7. 2025Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
  8. 2024Subtoxic Questions: Dive Into Attitude Change of LLM's Response in Jailbreak Attempts