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

@inproceedings{iclr2024_fine_34980,
  title = {{Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18094},
}

@inproceedings{icml2023_poisoning_42041,
  title = {{Poisoning Language Models During Instruction Tuning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/24997},
}

@inproceedings{iclr2024_badedit_34834,
  title = {{BadEdit: Backdooring Large Language Models by Model Editing}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18240},
}

@inproceedings{aaai2024_sentinellms_7317,
  title = {{SentinelLMs: Encrypted Input Adaptation and Fine-Tuning of Language Models for Private and Secure Inference}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30136},
}

@inproceedings{aaai2025_scaling_10690,
  title = {{Scaling Trends for Data Poisoning in LLMs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34929},
}

@inproceedings{neurips2024_backdooralign_70221,
  title = {{BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96865},
}

@inproceedings{neurips2024_alignment_70570,
  title = {{Alignment for Honesty}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96547},
}

@inproceedings{neurips2024_lisa_72164,
  title = {{Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95174},
}

@inproceedings{aaai2025_simulate_10766,
  title = {{Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32018},
}

@inproceedings{icml2024_privacy_45279,
  title = {{Privacy-Preserving Instructions for Aligning Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33173},
}

@inproceedings{neurips2024_risk_70205,
  title = {{Risk-Averse Fine-tuning of Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96880},
}

@inproceedings{neurips2024_huref_72187,
  title = {{HuRef: HUman-REadable Fingerprint for Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95154},
}

@inproceedings{iclr2025_safety_80874,
  title = {{Safety Alignment Should be Made More Than Just a Few Tokens Deep}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30893},
}

@inproceedings{aaai2025_scaleot_10686,
  title = {{ScaleOT: Privacy-utility-scalable Offsite-tuning with Dynamic LayerReplace and Selective Rank Compression}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34360},
}

@inproceedings{neurips2024_exploiting_71493,
  title = {{Exploiting LLM Quantization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95767},
}

@inproceedings{neurips2024_what_71538,
  title = {{What Makes and Breaks Safety Fine-tuning? A Mechanistic Study}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95726},
}

@inproceedings{neurips2024_vaccine_73698,
  title = {{Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93799},
}

@inproceedings{iclr2025_reef_82211,
  title = {{REEF: Representation Encoding Fingerprints for Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29580},
}

@inproceedings{aaai2025_df_8602,
  title = {{DF-MIA: A Distribution-Free Membership Inference Attack on Fine-Tuned Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32012},
}

@inproceedings{aaai2025_nlsr_10085,
  title = {{NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34762},
}

@inproceedings{iclr2024_unmasking_33687,
  title = {{Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19388},
}