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 26 / 26 页

  1. NeurIPS 2023On the Adversarial Robustness of Out-of-distribution Generalization Models
  2. NeurIPS 2023On the Robustness of Mechanism Design under Total Variation Distance
  3. NeurIPS 2023On Transfer of Adversarial Robustness from Pretraining to Downstream Tasks
  4. NeurIPS 2023One Less Reason for Filter Pruning: Gaining Free Adversarial Robustness with Structured Grouped Kernel Pruning
  5. NeurIPS 2023Optimal Transport Model Distributional Robustness
  6. NeurIPS 2023PAC-Bayesian Spectrally-Normalized Bounds for Adversarially Robust Generalization
  7. NeurIPS 2023Perturbation Towards Easy Samples Improves Targeted Adversarial Transferability
  8. NeurIPS 2023Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More
  9. NeurIPS 2023QuadAttac$K$: A Quadratic Programming Approach to Learning Ordered Top-$K$ Adversarial Attacks
  10. NeurIPS 2023Rethinking the Backward Propagation for Adversarial Transferability
  11. NeurIPS 2023Revisiting Adversarial Robustness Distillation from the Perspective of Robust Fairness
  12. NeurIPS 2023Revisiting Visual Model Robustness: A Frequency Long-Tailed Distribution View
  13. NeurIPS 2023Robust Data Valuation with Weighted Banzhaf Values
  14. NeurIPS 2023Robust Lipschitz Bandits to Adversarial Corruptions
  15. NeurIPS 2023Robust low-rank training via approximate orthonormal constraints
  16. NeurIPS 2023Robust Matrix Sensing in the Semi-Random Model
  17. NeurIPS 2023Robustness Guarantees for Adversarially Trained Neural Networks
  18. NeurIPS 2023RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletion
  19. NeurIPS 2023Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples
  20. NeurIPS 2023Spatial-frequency channels, shape bias, and adversarial robustness
  21. NeurIPS 2023Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases
  22. NeurIPS 2023Stable Diffusion is Unstable
  23. NeurIPS 2023Static and Sequential Malicious Attacks in the Context of Selective Forgetting
  24. NeurIPS 2023Strong and Precise Modulation of Human Percepts via Robustified ANNs
  25. NeurIPS 2023Temporal Robustness against Data poisoning
  26. NeurIPS 2023The Adversarial Consistency of Surrogate Risks for Binary Classification
  27. NeurIPS 2023The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks
  28. NeurIPS 2023Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly
  29. NeurIPS 2023Towards Higher Ranks via Adversarial Weight Pruning
  30. NeurIPS 2023Towards Last-layer Retraining for Group Robustness with Fewer Annotations
  31. NeurIPS 2023Training on Foveated Images Improves Robustness to Adversarial Attacks
  32. NeurIPS 2023Transferable Adversarial Robustness for Categorical Data via Universal Robust Embeddings
  33. NeurIPS 2023Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships
  34. NeurIPS 2023Understanding and Improving Ensemble Adversarial Defense
  35. NeurIPS 2023UniT: A Unified Look at Certified Robust Training against Text Adversarial Perturbation
  36. NeurIPS 2023Unlocking Deterministic Robustness Certification on ImageNet
  37. NeurIPS 2023VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models
  38. NeurIPS 2023Wasserstein distributional robustness of neural networks
  39. NeurIPS 2023What Can We Learn from Unlearnable Datasets?
  40. NeurIPS 2023What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners?

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