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 14 / 26 页

  1. CVPR 2024Attack To Defend: Exploiting Adversarial Attacks for Detecting Poisoned Models
  2. CVPR 2024Boosting Adversarial Training via Fisher-Rao Norm-based Regularization
  3. CVPR 2024Boosting Adversarial Transferability by Block Shuffle and Rotation
  4. CVPR 2024CausalPC: Improving the Robustness of Point Cloud Classification by Causal Effect Identification
  5. CVPR 2024DAP: A Dynamic Adversarial Patch for Evading Person Detectors
  6. CVPR 2024Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization
  7. CVPR 2024Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay
  8. CVPR 2024DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection
  9. CVPR 2024Dispel Darkness for Better Fusion: A Controllable Visual Enhancer based on Cross-modal Conditional Adversarial Learning
  10. CVPR 2024Ensemble Diversity Facilitates Adversarial Transferability
  11. CVPR 2024ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations
  12. CVPR 2024Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training
  13. CVPR 2024Friendly Sharpness-Aware Minimization
  14. CVPR 2024Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds
  15. CVPR 2024Improving Transferable Targeted Adversarial Attacks with Model Self-Enhancement
  16. CVPR 2024Incorporating Geo-Diverse Knowledge into Prompting for Increased Geographical Robustness in Object Recognition
  17. CVPR 2024Infrared Adversarial Car Stickers
  18. CVPR 2024Initialization Matters for Adversarial Transfer Learning
  19. CVPR 2024Label-Efficient Group Robustness via Out-of-Distribution Concept Curation
  20. CVPR 2024Language-Driven Anchors for Zero-Shot Adversarial Robustness
  21. CVPR 2024Learning to Transform Dynamically for Better Adversarial Transferability
  22. CVPR 2024MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model
  23. CVPR 2024MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models
  24. CVPR 2024Model Inversion Robustness: Can Transfer Learning Help?
  25. CVPR 2024NAPGuard: Towards Detecting Naturalistic Adversarial Patches
  26. CVPR 2024On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation
  27. CVPR 2024On the Robustness of Large Multimodal Models Against Image Adversarial Attacks
  28. CVPR 2024One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models
  29. CVPR 2024PAD: Patch-Agnostic Defense against Adversarial Patch Attacks
  30. CVPR 2024PeerAiD: Improving Adversarial Distillation from a Specialized Peer Tutor
  31. CVPR 2024Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving
  32. CVPR 2024Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness
  33. CVPR 2024Revisiting Adversarial Training at Scale
  34. CVPR 2024Revisiting Adversarial Training Under Long-Tailed Distributions
  35. CVPR 2024Robust Distillation via Untargeted and Targeted Intermediate Adversarial Samples
  36. CVPR 2024Robust Image Denoising through Adversarial Frequency Mixup
  37. CVPR 2024Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM
  38. CVPR 2024RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
  39. CVPR 2024Semantic-Aware Multi-Label Adversarial Attacks
  40. CVPR 2024SlowFormer: Adversarial Attack on Compute and Energy Consumption of Efficient Vision Transformers
  41. CVPR 2024Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement
  42. CVPR 2024Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning
  43. CVPR 2024Structure-Guided Adversarial Training of Diffusion Models
  44. CVPR 2024Structured Gradient-based Interpretations via Norm-Regularized Adversarial Training
  45. CVPR 2024Towards Fairness-Aware Adversarial Learning
  46. CVPR 2024Towards Robust 3D Pose Transfer with Adversarial Learning
  47. CVPR 2024Towards Transferable Targeted 3D Adversarial Attack in the Physical World
  48. CVPR 2024Towards Understanding and Improving Adversarial Robustness of Vision Transformers
  49. CVPR 2024Transferable Structural Sparse Adversarial Attack Via Exact Group Sparsity Training
  50. CVPR 2024Unexplored Faces of Robustness and Out-of-Distribution: Covariate Shifts in Environment and Sensor Domains

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