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 313 篇，第 5 / 7 页

  1. ICML 2023Robust Perception through Equivariance
  2. ICML 2023Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?
  3. ICML 2023Robustness in Multimodal Learning under Train-Test Modality Mismatch
  4. ICML 2023Run-off Election: Improved Provable Defense against Data Poisoning Attacks
  5. ICML 2023Simple and Fast Group Robustness by Automatic Feature Reweighting
  6. ICML 2023Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation
  7. ICML 2023Stratified Adversarial Robustness with Rejection
  8. ICML 2023The multimarginal optimal transport formulation of adversarial multiclass classification
  9. ICML 2023Towards Reliable Neural Specifications
  10. ICML 2023Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks
  11. ICML 2023Training-Free Neural Active Learning with Initialization-Robustness Guarantees
  12. ICML 2023Understanding and Defending Patched-based Adversarial Attacks for Vision Transformer
  13. ICML 2023Understanding the Impact of Adversarial Robustness on Accuracy Disparity
  14. NeurIPS 2023A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)
  15. NeurIPS 2023Adversarial Examples Are Not Real Features
  16. NeurIPS 2023Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces
  17. NeurIPS 2023Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness
  18. NeurIPS 2023Adversarial Learning for Feature Shift Detection and Correction
  19. NeurIPS 2023Adversarial Resilience in Sequential Prediction via Abstention
  20. NeurIPS 2023Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach
  21. NeurIPS 2023Adversarial Robustness through Random Weight Sampling
  22. NeurIPS 2023Adversarial Self-Training Improves Robustness and Generalization for Gradual Domain Adaptation
  23. NeurIPS 2023Adversarial Training from Mean Field Perspective
  24. NeurIPS 2023AND: Adversarial Neural Degradation for Learning Blind Image Super-Resolution
  25. NeurIPS 2023Asymmetric Certified Robustness via Feature-Convex Neural Networks
  26. NeurIPS 2023Asynchronous Proportional Response Dynamics: Convergence in Markets with Adversarial Scheduling
  27. NeurIPS 2023Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective
  28. NeurIPS 2023Batchnorm Allows Unsupervised Radial Attacks
  29. NeurIPS 2023Benchmarking Robustness to Adversarial Image Obfuscations
  30. NeurIPS 2023Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense
  31. NeurIPS 2023Blurred-Dilated Method for Adversarial Attacks
  32. NeurIPS 2023Boosting Adversarial Transferability by Achieving Flat Local Maxima
  33. NeurIPS 2023Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits
  34. NeurIPS 2023CamoPatch: An Evolutionary Strategy for Generating Camoflauged Adversarial Patches
  35. NeurIPS 2023Certifiably Robust Graph Contrastive Learning
  36. NeurIPS 2023Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization
  37. NeurIPS 2023Characterizing the Optimal $0-1$ Loss for Multi-class Classification with a Test-time Attacker
  38. NeurIPS 2023Color Equivariant Convolutional Networks
  39. NeurIPS 2023Connecting Certified and Adversarial Training
  40. NeurIPS 2023Content-based Unrestricted Adversarial Attack
  41. NeurIPS 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
  42. NeurIPS 2023Designing Robust Transformers using Robust Kernel Density Estimation
  43. NeurIPS 2023DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
  44. NeurIPS 2023Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability
  45. NeurIPS 2023Distribution Learnability and Robustness
  46. NeurIPS 2023Dynamic Regret of Adversarial Linear Mixture MDPs
  47. NeurIPS 2023Dynamically Masked Discriminator for GANs
  48. NeurIPS 2023Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection
  49. NeurIPS 2023Efficient Testable Learning of Halfspaces with Adversarial Label Noise
  50. NeurIPS 2023Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization

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