mlsanityData to 14 Oct 2026

Geneshift: Impact of different scenario shift on Jailbreaking LLM

arXiv 2504.08104 ↗First posted 10 Apr 2025cs.CR cs.AI cs.CLcited by 5

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

Jailbreak attacks, which aim to cause LLMs to perform unrestricted behaviors, have become a critical and challenging direction in AI safety. Despite achieving the promising attack success rate using dictionary-based evaluation, existing jailbreak attack methods fail to output detailed contents to satisfy the harmful request, leading to poor performance on GPT-based evaluation. To this end, we propose a black-box jailbreak attack termed GeneShift, by using a genetic algorithm to optimize the scenario shifts. Firstly, we observe that the malicious queries perform optimally under different scenario shifts. Based on it, we develop a genetic algorithm to evolve and select the hybrid of scenario shifts. It guides our method to elicit detailed and actionable harmful responses while keeping the seemingly benign facade, improving stealthiness. Extensive experiments demonstrate the superiority of GeneShift. Notably, GeneShift increases the jailbreak success rate from 0% to 60% when direct prompting alone would fail.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 39 of its 45 references that are in the map. First posted on arXiv 10 Apr 2025.

Builds on

39 of 45 references.

Closest ancestors · 21

Same direction, newest first

  1. 2024FlipAttack: Jailbreak LLMs via Flipping2 Oct
  2. 2024GPT-4 Jailbreaks Itself with Near-Perfect Success Using Self-Explanation21 May
  3. 2024Boosting Jailbreak Attack with Momentum2 May
  4. 2024Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models26 Mar
  5. 2024Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction28 Feb
  6. 2024Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing25 Feb
  7. 2024SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding14 Feb
  8. 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automatically4 Dec
  9. 2023Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization15 Nov
  10. 2023A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily14 Nov
  11. 2023Jailbreaking Black Box Large Language Models in Twenty Queries12 Oct
  12. 2023Multilingual Jailbreak Challenges in Large Language Models10 Oct
9 more
  1. 2023SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks5 Oct
  2. 2023AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models3 Oct
  3. 2023Low-Resource Languages Jailbreak GPT-43 Oct
  4. 2023GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts19 Sep
  5. 2023Detecting Language Model Attacks with Perplexity27 Aug
  6. 2023GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher12 Aug
  7. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul
  8. 2023MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots16 Jul
  9. 2023Jailbroken: How Does LLM Safety Training Fail?5 Jul

Other references · 18

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  4. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,207
  5. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,154
  6. 2023Safe RLHF: Safe Reinforcement Learning from Human Feedbackcited by 656
  7. 2024WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMscited by 496
  8. 2023LLM Self Defense: By Self Examination, LLMs Know They Are Being Trickedcited by 244
  9. 2024ShieldGemma: Generative AI Content Moderation Based on Gemmacited by 243
  10. 2024ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMscited by 216
  11. 2023MART: Improving LLM Safety with Multi-round Automatic Red-Teamingcited by 163
  12. 2022COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamicscited by 161
6 more
  1. 2023RAIN: Your Language Models Can Align Themselves without Finetuningcited by 157
  2. 2024AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Expertscited by 136
  3. 2023An LLM can Fool Itself: A Prompt-Based Adversarial Attackcited by 116
  4. 2024On Prompt-Driven Safeguarding for Large Language Modelscited by 116
  5. 2025GuardReasoner: Towards Reasoning-based LLM Safeguardscited by 100
  6. 2024Detoxifying Large Language Models via Knowledge Editingcited by 87

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 116
  2. 2026MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safetycited by 21
  3. 2025Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Modelscited by 19
  4. 2026JailbreakSkill: Scaling Automated Red-Teaming with Reusable and Ever-Evolving Skillscited by 3
  5. 2026GAS-Leak-LLM: Genetic Algorithm-Based Suffix Optimization for Black-Box LLM Jailbreakingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026EvoJail: Evolutionary Diverse Jailbreak Prompt Generation for Large Language Models
  2. 2024AutoJailbreak: Exploring Jailbreak Attacks and Defenses through a Dependency Lens
  3. 2025Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space
  4. 2025Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience
  5. 2024Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs
  6. 2025GeneBreaker: Jailbreak Attacks against DNA Language Models with Pathogenicity Guidance
  7. 2026JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization
  8. 2024BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Models