% Key papers for Defenses against universal perturbations (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2017_universal_12716,
  title = {{Universal Adversarial Perturbations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{iclr2018_defense_28443,
  title = {{Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/113},
}

@inproceedings{cvpr2018_defense_12993,
  title = {{Defense Against Universal Adversarial Perturbations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Akhtar_Defense_Against_Universal_CVPR_2018_paper.html},
}

@inproceedings{cvpr2022_las_19140,
  title = {{LAS-AT: Adversarial Training With Learnable Attack Strategy}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2018_nag_13414,
  title = {{NAG: Network for Adversary Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Mopuri_NAG_Network_for_CVPR_2018_paper.html},
}

@inproceedings{neurips2020_on_60456,
  title = {{On Adaptive Attacks to Adversarial Example Defenses}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18299},
}

@inproceedings{cvpr2020_understanding_16398,
  title = {{Understanding Adversarial Examples From the Mutual Influence of Images and Perturbations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2019_detection_14081,
  title = {{Detection Based Defense Against Adversarial Examples From the Steganalysis Point of View}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2019_rob_14743,
  title = {{Rob-GAN: Generator, Discriminator, and Adversarial Attacker}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{neurips2019_defense_58117,
  title = {{Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13390},
}

@inproceedings{aaai2020_stealthy_102185,
  title = {{Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6047},
}

@inproceedings{iclr2019_characterizing_29122,
  title = {{Characterizing Audio Adversarial Examples Using Temporal Dependency}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/1113},
}

@inproceedings{aaai2018_detecting_102561,
  title = {{Detecting Adversarial Examples Through Image Transformation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11828},
}

@inproceedings{aaai2019_adversarial_100181,
  title = {{Adversarial Learning for Weakly-Supervised Social Network Alignment}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/3889},
}

@inproceedings{aaai2020_ml_102278,
  title = {{ML-LOO: Detecting Adversarial Examples with Feature Attribution}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6140},
}

@inproceedings{neurips2020_adversarial_59345,
  title = {{Adversarial Self-Supervised Contrastive Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17078},
}

@inproceedings{aaai2019_resisting_99942,
  title = {{Resisting Adversarial Attacks Using Gaussian Mixture Variational Autoencoders}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/3828},
}

@inproceedings{neurips2019_a_57824,
  title = {{A New Defense Against Adversarial Images: Turning a Weakness into a Strength}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13374},
}

@inproceedings{aaai2021_adversarial_105,
  title = {{Adversarial Training with Fast Gradient Projection Method against Synonym Substitution Based Text Attacks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/13997-adversarial-training-with-fast-gradient-projection-method-against-synonym-substitution-based-text-attacks/},
}

@inproceedings{cvpr2020_single_16250,
  title = {{Single-Step Adversarial Training With Dropout Scheduling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{aaai2024_stable_7408,
  title = {{Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28169},
}

@inproceedings{aaai2024_limeattack_6530,
  title = {{LimeAttack: Local Explainable Method for Textual Hard-Label Adversarial Attack}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29950},
}

@inproceedings{aaai2025_improving_9532,
  title = {{Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33117},
}

@inproceedings{cvpr2025_patchguard_27229,
  title = {{PatchGuard: Adversarially Robust Anomaly Detection and Localization through Vision Transformers and Pseudo Anomalies}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32508},
}

@inproceedings{cvpr2024_semantic_24798,
  title = {{Semantic-Aware Multi-Label Adversarial Attacks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30652},
}

@inproceedings{cvpr2025_detecting_25908,
  title = {{Detecting Adversarial Data Using Perturbation Forgery}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34750},
}

@inproceedings{neurips2024_dat_72327,
  title = {{DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95020},
}

@inproceedings{aaai2024_adversarial_5145,
  title = {{Adversarial Attacks on the Interpretation of Neuron Activation Maximization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28228},
}

@inproceedings{aaai2025_learning_9757,
  title = {{Learning from Mistakes: Self-correct Adversarial Training for Chinese Unnatural Text Correction}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34561},
}

@inproceedings{cvpr2025_weakly_28147,
  title = {{Weakly Supervised Contrastive Adversarial Training for Learning Robust Features from Semi-supervised Data}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33596},
}

@inproceedings{icml2024_purify_43246,
  title = {{Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35206},
}

@inproceedings{icml2024_be_44425,
  title = {{Be Your Own Neighborhood: Detecting Adversarial Examples by the Neighborhood Relations Built on Self-Supervised Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34027},
}

@inproceedings{neurips2024_feature_72178,
  title = {{Feature-Level Adversarial Attacks and Ranking Disruption for Visible-Infrared Person Re-identification}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95162},
}

@inproceedings{cvpr2024_re_24582,
  title = {{Re-thinking Data Availability Attacks Against Deep Neural Networks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30806},
}

@inproceedings{icml2024_datafreeshield_45567,
  title = {{DataFreeShield: Defending Adversarial Attacks without Training Data}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32885},
}

@inproceedings{aaai2026_rethinking_104122,
  title = {{Rethinking Target Label Conditioning in Adversarial Attacks: A 2D Tensor-Guided Generative Approach}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37651},
}

@inproceedings{aaai2025_does_8793,
  title = {{Does Knowing More Make You Easier to Trick? Adversarial Robustness of Multi-Target Regression}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35328},
}

@inproceedings{neurips2024_generate_72085,
  title = {{Generate Universal Adversarial Perturbations for Few-Shot Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95241},
}

@inproceedings{neurips2024_rapid_72377,
  title = {{Rapid Plug-in Defenders}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94975},
}

@inproceedings{neurips2025_frameshield_75363,
  title = {{FrameShield: Adversarially Robust Video Anomaly Detection}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=7FLKzOqsKd},
}