对抗鲁棒论文趋势 2023–2026

对抗样本与防御

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,291 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

对抗鲁棒论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023100796074313
2024131707360334
2025110888544327
202681949349317

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部对抗鲁棒论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 1,290 篇，第 21 / 26 页

  1. CVPR 2023FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits
  2. CVPR 2023GANmouflage: 3D Object Nondetection With Texture Fields
  3. CVPR 2023Generalist: Decoupling Natural and Robust Generalization
  4. CVPR 2023ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing
  5. CVPR 2023Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization
  6. CVPR 2023Improving Robustness of Semantic Segmentation to Motion-Blur Using Class-Centric Augmentation
  7. CVPR 2023Improving Robustness of Vision Transformers by Reducing Sensitivity To Patch Corruptions
  8. CVPR 2023Improving the Transferability of Adversarial Samples by Path-Augmented Method
  9. CVPR 2023Improving Zero-Shot Generalization and Robustness of Multi-Modal Models
  10. CVPR 2023Introducing Competition To Boost the Transferability of Targeted Adversarial Examples Through Clean Feature Mixup
  11. CVPR 2023Jedi: Entropy-Based Localization and Removal of Adversarial Patches
  12. CVPR 2023Label-Free Liver Tumor Segmentation
  13. CVPR 2023Learning To Retain While Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation
  14. CVPR 2023Learning With Noisy Labels via Self-Supervised Adversarial Noisy Masking
  15. CVPR 2023Masked Auto-Encoders Meet Generative Adversarial Networks and Beyond
  16. CVPR 2023Multi-View Adversarial Discriminator: Mine the Non-Causal Factors for Object Detection in Unseen Domains
  17. CVPR 2023Open-Set Semantic Segmentation for Point Clouds via Adversarial Prototype Framework
  18. CVPR 2023PEFAT: Boosting Semi-Supervised Medical Image Classification via Pseudo-Loss Estimation and Feature Adversarial Training
  19. CVPR 2023Physical-World Optical Adversarial Attacks on 3D Face Recognition
  20. CVPR 2023Physically Adversarial Infrared Patches With Learnable Shapes and Locations
  21. CVPR 2023PointCert: Point Cloud Classification With Deterministic Certified Robustness Guarantees
  22. CVPR 2023PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation
  23. CVPR 2023Privacy-Preserving Adversarial Facial Features
  24. CVPR 2023Progressive Backdoor Erasing via Connecting Backdoor and Adversarial Attacks
  25. CVPR 2023Proximal Splitting Adversarial Attack for Semantic Segmentation
  26. CVPR 2023Randomized Adversarial Training via Taylor Expansion
  27. CVPR 2023Rate Gradient Approximation Attack Threats Deep Spiking Neural Networks
  28. CVPR 2023Revisiting Residual Networks for Adversarial Robustness
  29. CVPR 2023RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural Prompts
  30. CVPR 2023Robust Dynamic Radiance Fields
  31. CVPR 2023Robust Single Image Reflection Removal Against Adversarial Attacks
  32. CVPR 2023Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts
  33. CVPR 2023Semi-Supervised Hand Appearance Recovery via Structure Disentanglement and Dual Adversarial Discrimination
  34. CVPR 2023Sibling-Attack: Rethinking Transferable Adversarial Attacks Against Face Recognition
  35. CVPR 2023SlowLiDAR: Increasing the Latency of LiDAR-Based Detection Using Adversarial Examples
  36. CVPR 2023StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learning
  37. CVPR 2023StyLess: Boosting the Transferability of Adversarial Examples
  38. CVPR 2023Super-CLEVR: A Virtual Benchmark To Diagnose Domain Robustness in Visual Reasoning
  39. CVPR 2023Teacher-Generated Spatial-Attention Labels Boost Robustness and Accuracy of Contrastive Models
  40. CVPR 2023TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation
  41. CVPR 2023The Best Defense Is a Good Offense: Adversarial Augmentation Against Adversarial Attacks
  42. CVPR 2023The Enemy of My Enemy Is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training
  43. CVPR 2023Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks
  44. CVPR 2023Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations
  45. CVPR 2023Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition
  46. CVPR 2023Towards Transferable Targeted Adversarial Examples
  47. CVPR 2023Trade-Off Between Robustness and Accuracy of Vision Transformers
  48. CVPR 2023Turning Strengths Into Weaknesses: A Certified Robustness Inspired Attack Framework Against Graph Neural Networks
  49. CVPR 2023TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization
  50. CVPR 2023Understanding the Robustness of 3D Object Detection With Bird's-Eye-View Representations in Autonomous Driving

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查对抗鲁棒在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "adversarial-robustness"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇对抗鲁棒论文？
共 1,291 篇，按年份分别是 2023 年 313 篇、2024 年 334 篇、2025 年 327 篇、2026 年 317 篇。
NeurIPS 2026 有多少篇对抗鲁棒论文？
NeurIPS 2026 有 81 篇对抗鲁棒论文，上一届是 110 篇。
ICLR 2026 有多少篇对抗鲁棒论文？
ICLR 2026 有 94 篇对抗鲁棒论文，上一届是 88 篇。
ICML 2026 有多少篇对抗鲁棒论文？
ICML 2026 有 93 篇对抗鲁棒论文，上一届是 85 篇。
CVPR 2026 有多少篇对抗鲁棒论文？
CVPR 2026 有 49 篇对抗鲁棒论文，上一届是 44 篇。
哪个会议的对抗鲁棒论文最多？
NeurIPS，2023–2026 年共 422 篇。

「安全与可信」下的其他主题