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

@inproceedings{neurips2024_many_73054,
  title = {{Many-shot Jailbreaking}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94370},
}

@inproceedings{neurips2024_wildteaming_73790,
  title = {{WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93716},
}

@inproceedings{neurips2024_improved_74634,
  title = {{Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/92958},
}

@inproceedings{aaai2025_diver_8779,
  title = {{DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34797},
}

@inproceedings{icml2025_weak_46225,
  title = {{Weak-to-Strong Jailbreaking on Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46335},
}

@inproceedings{neurips2024_navigating_71353,
  title = {{Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95896},
}

@inproceedings{neurips2024_uncovering_72423,
  title = {{Uncovering Safety Risks of Large Language Models through Concept Activation Vector}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94933},
}

@inproceedings{neurips2024_protecting_74267,
  title = {{Protecting Your LLMs with Information Bottleneck}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93290},
}

@inproceedings{neurips2025_refusal_78431,
  title = {{Refusal Direction is Universal Across Safety-Aligned Languages}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=eWxKpdAdXH},
}

@inproceedings{aaai2025_all_8086,
  title = {{All You Need Is S P A C E: When Jailbreaking Meets Bias Audit and Reveals What Lies Beneath the Guardrails (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35249},
}

@inproceedings{aaai2025_investigating_9604,
  title = {{Investigating the Security Threat Arising from “Yes-No” Implicit Bias in Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34554},
}

@inproceedings{icml2025_cannot_46173,
  title = {{Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46387},
}

@inproceedings{icml2025_emoji_47231,
  title = {{Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45356},
}

@inproceedings{icml2025_speak_48131,
  title = {{Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44478},
}

@inproceedings{icml2026_persistbench_52796,
  title = {{PersistBench: When Should Long-Term Memories Be Forgotten by LLMs?}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=Z7Rhzk13NT},
}

@inproceedings{neurips2025_advprefix_77154,
  title = {{AdvPrefix: An Objective for Nuanced LLM Jailbreaks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=R0B1z8dQcV},
}

@inproceedings{iclr2026_asguard_89254,
  title = {{ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=wmiEXNEXPs},
}

@inproceedings{aaai2026_response_108484,
  title = {{Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40836},
}

@inproceedings{icml2025_hidden_47259,
  title = {{Hidden No More: Attacking and Defending Private Third-Party LLM Inference}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45330},
}

@inproceedings{iclr2025_beyond_83645,
  title = {{Beyond Mere Token Analysis: A Hypergraph Metric Space Framework for Defending Against Socially Engineered LLM Attacks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28172},
}