% Key papers for Safety alignment of LLMs (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2024_wildguard_71500,
  title = {{WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97764},
}

@inproceedings{aaai2024_llmguard_6406,
  title = {{LLMGuard: Guarding against Unsafe LLM Behavior}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30566},
}

@inproceedings{neurips2024_sg_72968,
  title = {{SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97610},
}

@inproceedings{aaai2025_security_10704,
  title = {{Security Attacks on LLM-based Code Completion Tools}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34537},
}

@inproceedings{icml2025_or_46516,
  title = {{OR-Bench: An Over-Refusal Benchmark for Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46052},
}

@inproceedings{iclr2024_tensor_34906,
  title = {{Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18168},
}

@inproceedings{neurips2024_mllmguard_73561,
  title = {{MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97540},
}

@inproceedings{icml2024_on_45638,
  title = {{On Prompt-Driven Safeguarding for Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32814},
}

@inproceedings{iclr2025_sorry_82544,
  title = {{SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29252},
}

@inproceedings{aaai2026_mpma_108546,
  title = {{MPMA: Preference Manipulation Attack Against Model Context Protocol}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40898},
}

@inproceedings{aaai2025_scans_10594,
  title = {{SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34521},
}

@inproceedings{neurips2024_soft_71062,
  title = {{Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96148},
}

@inproceedings{aaai2025_seas_10601,
  title = {{SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34549},
}

@inproceedings{aaai2025_rtp_10454,
  title = {{RTP-LX: Can LLMs Evaluate Toxicity in Multilingual Scenarios?}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35011},
}

@inproceedings{aaai2025_safeinfer_10663,
  title = {{SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34927},
}

@inproceedings{icml2024_learning_44403,
  title = {{Learning and Forgetting Unsafe Examples in Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34049},
}

@inproceedings{neurips2024_toxicity_70529,
  title = {{Toxicity Detection for Free}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96583},
}

@inproceedings{icml2024_rigorllm_44354,
  title = {{RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34098},
}

@inproceedings{icml2025_automated_47848,
  title = {{Automated Red Teaming with GOAT: the Generative Offensive Agent Tester}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44754},
}

@inproceedings{neurips2024_who_73164,
  title = {{Who's asking? User personas and the mechanics of latent misalignment}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94269},
}