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 24 / 26 页

  1. ICML 2023Efficient Rate Optimal Regret for Adversarial Contextual MDPs Using Online Function Approximation
  2. ICML 2023Eliminating Adversarial Noise via Information Discard and Robust Representation Restoration
  3. ICML 2023Extending Kernel PCA through Dualization: Sparsity, Robustness and Fast Algorithms
  4. ICML 2023Federated Adversarial Learning: A Framework with Convergence Analysis
  5. ICML 2023From Robustness to Privacy and Back
  6. ICML 2023GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks
  7. ICML 2023How Many Perturbations Break This Model? Evaluating Robustness Beyond Adversarial Accuracy
  8. ICML 2023Identification of the Adversary from a Single Adversarial Example
  9. ICML 2023Improved Algorithms for White-Box Adversarial Streams
  10. ICML 2023Improving Adversarial Robustness by Putting More Regularizations on Less Robust Samples
  11. ICML 2023Improving Adversarial Robustness of Deep Equilibrium Models with Explicit Regulations Along the Neural Dynamics
  12. ICML 2023Improving Adversarial Robustness Through the Contrastive-Guided Diffusion Process
  13. ICML 2023Improving l1-Certified Robustness via Randomized Smoothing by Leveraging Box Constraints
  14. ICML 2023Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity
  15. ICML 2023Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees
  16. ICML 2023MultiRobustBench: Benchmarking Robustness Against Multiple Attacks
  17. ICML 2023NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations
  18. ICML 2023On the Robustness of Randomized Ensembles to Adversarial Perturbations
  19. ICML 2023On the Robustness of Text Vectorizers
  20. ICML 2023One-vs-the-Rest Loss to Focus on Important Samples in Adversarial Training
  21. ICML 2023Online Nonstochastic Control with Adversarial and Static Constraints
  22. ICML 2023Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization
  23. ICML 2023Phase-aware Adversarial Defense for Improving Adversarial Robustness
  24. ICML 2023Probabilistic Categorical Adversarial Attack and Adversarial Training
  25. ICML 2023Reasons for the Superiority of Stochastic Estimators over Deterministic Ones: Robustness, Consistency and Perceptual Quality
  26. ICML 2023Recovery Bounds on Class-Based Optimal Transport: A Sum-of-Norms Regularization Framework
  27. ICML 2023Refined Regret for Adversarial MDPs with Linear Function Approximation
  28. ICML 2023Robust Perception through Equivariance
  29. ICML 2023Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?
  30. ICML 2023Robustness in Multimodal Learning under Train-Test Modality Mismatch
  31. ICML 2023Run-off Election: Improved Provable Defense against Data Poisoning Attacks
  32. ICML 2023Simple and Fast Group Robustness by Automatic Feature Reweighting
  33. ICML 2023Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation
  34. ICML 2023Stratified Adversarial Robustness with Rejection
  35. ICML 2023The multimarginal optimal transport formulation of adversarial multiclass classification
  36. ICML 2023Towards Reliable Neural Specifications
  37. ICML 2023Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks
  38. ICML 2023Training-Free Neural Active Learning with Initialization-Robustness Guarantees
  39. ICML 2023Understanding and Defending Patched-based Adversarial Attacks for Vision Transformer
  40. ICML 2023Understanding the Impact of Adversarial Robustness on Accuracy Disparity
  41. NeurIPS 2023A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)
  42. NeurIPS 2023Adversarial Examples Are Not Real Features
  43. NeurIPS 2023Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces
  44. NeurIPS 2023Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness
  45. NeurIPS 2023Adversarial Learning for Feature Shift Detection and Correction
  46. NeurIPS 2023Adversarial Resilience in Sequential Prediction via Abstention
  47. NeurIPS 2023Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach
  48. NeurIPS 2023Adversarial Robustness through Random Weight Sampling
  49. NeurIPS 2023Adversarial Self-Training Improves Robustness and Generalization for Gradual Domain Adaptation
  50. NeurIPS 2023Adversarial Training from Mean Field Perspective

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