% Key papers for Jailbreak attacks and defenses (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2023_jailbroken_69184,
  title = {{Jailbroken: How Does LLM Safety Training Fail?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70702},
}

@inproceedings{neurips2024_tree_72266,
  title = {{Tree of Attacks: Jailbreaking Black-Box LLMs Automatically}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95078},
}

@inproceedings{iclr2024_autodan_33709,
  title = {{AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19366},
}

@inproceedings{neurips2024_a_71617,
  title = {{A StrongREJECT for Empty Jailbreaks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97752},
}

@inproceedings{iclr2024_multilingual_35530,
  title = {{Multilingual Jailbreak Challenges in Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17543},
}

@inproceedings{aaai2025_multi_10036,
  title = {{Multi-Turn Jailbreaking Large Language Models via Attention Shifting}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34553},
}

@inproceedings{iclr2024_catastrophic_35367,
  title = {{Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17706},
}

@inproceedings{cvpr2025_playing_27262,
  title = {{Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34727},
}

@inproceedings{icml2024_cold_45786,
  title = {{COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32666},
}

@inproceedings{neurips2024_jailbreaking_70960,
  title = {{Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96243},
}

@inproceedings{neurips2024_bag_74586,
  title = {{Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97431},
}

@inproceedings{aaai2025_token_11014,
  title = {{Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34943},
}

@inproceedings{iclr2025_jailbreak_83667,
  title = {{Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28150},
}

@inproceedings{neurips2024_efficient_72922,
  title = {{Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94489},
}

@inproceedings{iclr2025_improved_82854,
  title = {{Improved Techniques for Optimization-Based Jailbreaking on Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28946},
}

@inproceedings{aaai2025_llm_9673,
  title = {{LLM Stinger: Jailbreaking LLMs Using RL Fine-Tuned LLMs (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35263},
}

@inproceedings{icml2026_multibreak_52477,
  title = {{MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=WR1IcmCjbl},
}

@inproceedings{neurips2025_adjacent_76170,
  title = {{Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=GLhLU6y1uK},
}

@inproceedings{iclr2026_safedialbench_85955,
  title = {{SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=KFjtRqVnKH},
}

@inproceedings{iclr2026_guidedbench_87246,
  title = {{GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=ZVg8y3ibyM},
}

@inproceedings{iclr2026_align_87854,
  title = {{Align to Misalign: Automatic LLM Jailbreak with Meta-Optimized LLM Judges}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=gGjwMNAYAr},
}