% Key papers for Differentially private synthetic data (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{iclr2018_learning_28422,
  title = {{Learning Differentially Private Recurrent Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/187},
}

@inproceedings{iclr2019_pate_29029,
  title = {{PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/880},
}

@inproceedings{iclr2022_large_31461,
  title = {{Large Language Models Can Be Strong Differentially Private Learners}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6894},
}

@inproceedings{neurips2020_gs_59923,
  title = {{GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18617},
}

@inproceedings{iclr2022_differentially_31254,
  title = {{Differentially Private Fine-tuning of Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/7161},
}

@inproceedings{iclr2020_generative_29631,
  title = {{Generative Models for Effective ML on Private, Decentralized Datasets}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=SJgaRA4FPH},
}

@inproceedings{neurips2021_g_62570,
  title = {{G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27840},
}

@inproceedings{aaai2022_differentially_1980,
  title = {{Differentially Private Normalizing Flows for Synthetic Tabular Data Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/07345-differentially-private-normalizing-flows-for-synthetic-tabular-data-generation/},
}

@inproceedings{cvpr2022_dpgen_18583,
  title = {{DPGEN: Differentially Private Generative Energy-Guided Network for Natural Image Synthesis}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{neurips2022_private_65927,
  title = {{Private Set Generation with Discriminative Information}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53552},
}

@inproceedings{iclr2021_private_30018,
  title = {{Private Post-GAN Boosting}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/3202},
}

@inproceedings{icml2022_robin_41106,
  title = {{Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Data}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/18247},
}

@inproceedings{iclr2024_privacy_35261,
  title = {{Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17812},
}

@inproceedings{iclr2024_privacy_35602,
  title = {{Privacy-Preserving In-Context Learning for Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17471},
}

@inproceedings{neurips2023_flocks_69775,
  title = {{Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70167},
}

@inproceedings{iclr2022_pearl_31173,
  title = {{PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6335},
}

@inproceedings{aaai2025_dr_8622,
  title = {{DR-Encoder: Encode Low-rank Gradients with Random Prior for Large Language Models Differentially Privately}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34985},
}

@inproceedings{icml2024_cuts_44663,
  title = {{CuTS: Customizable Tabular Synthetic Data Generation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33789},
}

@inproceedings{neurips2022_seqpate_65279,
  title = {{SeqPATE: Differentially Private Text Generation via Knowledge Distillation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55068},
}

@inproceedings{aaai2024_analysis_5187,
  title = {{Analysis of Differentially Private Synthetic Data: A Measurement Error Approach}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30114},
}

@inproceedings{icml2024_differentially_44161,
  title = {{Differentially Private Synthetic Data via Foundation Model APIs 2: Text}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34291},
}

@inproceedings{iclr2025_pfguard_81028,
  title = {{PFGuard: A Generative Framework with Privacy and Fairness Safeguards}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30740},
}

@inproceedings{neurips2025_struct_75181,
  title = {{Struct-Bench: A Benchmark for Differentially Private Structured Text Generation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=59vXWteYuh},
}

@inproceedings{iclr2025_differentially_83290,
  title = {{Differentially Private Steering for Large Language Model Alignment}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28523},
}

@inproceedings{aaai2026_dp_104327,
  title = {{DP-GenG: Differentially Private Dataset Distillation Guided by DP-Generated Data}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37854},
}

@inproceedings{aaai2025_dp_8619,
  title = {{DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34830},
}

@inproceedings{iclr2024_efficiently_34079,
  title = {{Efficiently Computing Similarities to Private Datasets}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18996},
}

@inproceedings{iclr2024_differentially_34644,
  title = {{Differentially Private Synthetic Data via Foundation Model APIs 1: Images}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18430},
}

@inproceedings{icml2024_vip_43542,
  title = {{ViP: A Differentially Private Foundation Model for Computer Vision}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34910},
}

@inproceedings{icml2024_bounding_44622,
  title = {{Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33830},
}

@inproceedings{icml2025_scaling_46548,
  title = {{Scaling Laws for Differentially Private Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46020},
}

@inproceedings{icml2025_pcevolve_46835,
  title = {{PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative APIs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45741},
}

@inproceedings{icml2025_cape_47913,
  title = {{Cape: Context-Aware Prompt Perturbation Mechanism with Differential Privacy}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44690},
}

@inproceedings{icml2025_contrastive_48559,
  title = {{Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44062},
}

@inproceedings{icml2026_private_50488,
  title = {{Private and Stable Test-time Adaptation with Differential Privacy}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=Ct0HIcLIMX},
}