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

@inproceedings{neurips2020_inverting_60111,
  title = {{Inverting Gradients - How easy is it to break privacy in federated learning?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18574},
}

@inproceedings{cvpr2021_soteria_17917,
  title = {{Soteria: Provable Defense Against Privacy Leakage in Federated Learning From Representation Perspective}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2022_auditing_18311,
  title = {{Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakage}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{neurips2021_evaluating_61171,
  title = {{Evaluating Gradient Inversion Attacks and Defenses in Federated Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27236},
}

@inproceedings{cvpr2022_ressfl_19714,
  title = {{ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_april_18239,
  title = {{APRIL: Finding the Achilles' Heel on Privacy for Vision Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2024_towards_7631,
  title = {{Towards the Robustness of Differentially Private Federated Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29967},
}

@inproceedings{neurips2022_lamp_64035,
  title = {{LAMP: Extracting Text from Gradients with Language Model Priors}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/52794},
}

@inproceedings{neurips2022_recovering_65531,
  title = {{Recovering Private Text in Federated Learning of Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53215},
}

@inproceedings{aaai2023_dropout_3505,
  title = {{Dropout Is NOT All You Need to Prevent Gradient Leakage}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26163},
}

@inproceedings{aaai2024_high_6213,
  title = {{High-Fidelity Gradient Inversion in Distributed Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29975},
}

@inproceedings{iclr2022_bayesian_31521,
  title = {{Bayesian Framework for Gradient Leakage}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6934},
}

@inproceedings{neurips2021_cafe_62650,
  title = {{CAFE: Catastrophic Data Leakage in Vertical Federated Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26329},
}

@inproceedings{icml2022_fishing_40574,
  title = {{Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/16787},
}

@inproceedings{aaai2024_concealing_5460,
  title = {{Concealing Sensitive Samples against Gradient Leakage in Federated Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30171},
}

@inproceedings{cvpr2023_breaching_20510,
  title = {{Breaching FedMD: Image Recovery via Paired-Logits Inversion Attack}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23098},
}

@inproceedings{cvpr2023_the_22341,
  title = {{The Resource Problem of Using Linear Layer Leakage Attack in Federated Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21564},
}

@inproceedings{aaai2025_a_7912,
  title = {{A New Federated Learning Framework Against Gradient Inversion Attacks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33865},
}

@inproceedings{aaai2024_revisiting_7149,
  title = {{Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28460},
}

@inproceedings{iclr2023_decepticons_33229,
  title = {{Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/10839},
}

@inproceedings{neurips2024_dager_71096,
  title = {{DAGER: Exact Gradient Inversion for Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96118},
}

@inproceedings{cvpr2024_leak_23936,
  title = {{Leak and Learn: An Attacker's Cookbook to Train Using Leaked Data from Federated Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30694},
}

@inproceedings{cvpr2025_gradient_26448,
  title = {{Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33941},
}

@inproceedings{aaai2024_foreseeing_6041,
  title = {{Foreseeing Reconstruction Quality of Gradient Inversion: An Optimization Perspective}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29140},
}

@inproceedings{aaai2025_mj_9969,
  title = {{Mjölnir: Breaking the Shield of Perturbation-Protected Gradients via Adaptive Diffusion}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34829},
}

@inproceedings{neurips2024_spear_73659,
  title = {{SPEAR: Exact Gradient Inversion of Batches in Federated Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93833},
}

@inproceedings{neurips2024_datastealing_70642,
  title = {{DataStealing: Steal Data from Diffusion Models in Federated Learning with Multiple Trojans}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96480},
}

@inproceedings{aaai2025_exploit_9060,
  title = {{Exploit Gradient Skewness to Circumvent Byzantine Defenses for Federated Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34094},
}

@inproceedings{icml2024_recovering_43852,
  title = {{Recovering Labels from Local Updates in Federated Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34600},
}

@inproceedings{icml2024_privacy_45291,
  title = {{Privacy Attacks in Decentralized Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33161},
}

@inproceedings{icml2024_certifiably_43437,
  title = {{Certifiably Byzantine-Robust Federated Conformal Prediction}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35015},
}

@inproceedings{neurips2024_fedgmark_74508,
  title = {{FedGMark: Certifiably Robust Watermarking for Federated Graph Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93069},
}

@inproceedings{neurips2026_temporal_90005,
  title = {{Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/151269},
}

@inproceedings{neurips2026_leveraging_90210,
  title = {{Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/154096},
}

@inproceedings{aaai2026_enhanced_104214,
  title = {{Enhanced Privacy Leakage from Noise-Perturbed Gradients via Gradient-Guided Conditional Diffusion Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37743},
}