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 17 / 26 页

  1. ICML 2024Graph Adversarial Diffusion Convolution
  2. ICML 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
  3. ICML 2024How Smooth Is Attention?
  4. ICML 2024Imitation Learning in Discounted Linear MDPs without exploration assumptions
  5. ICML 2024Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training
  6. ICML 2024Improving Adversarial Energy-Based Model via Diffusion Process
  7. ICML 2024Improving Generalization in Offline Reinforcement Learning via Adversarial Data Splitting
  8. ICML 2024Improving Group Robustness on Spurious Correlation Requires Preciser Group Inference
  9. ICML 2024IOI: Invisible One-Iteration Adversarial Attack on No-Reference Image- and Video-Quality Metrics
  10. ICML 2024Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency
  11. ICML 2024Multigroup Robustness
  12. ICML 2024No Free Prune: Information-Theoretic Barriers to Pruning at Initialization
  13. ICML 2024Non-clairvoyant Scheduling with Partial Predictions
  14. ICML 2024On the Duality Between Sharpness-Aware Minimization and Adversarial Training
  15. ICML 2024Online Learning in CMDPs: Handling Stochastic and Adversarial Constraints
  16. ICML 2024Online Matching with Stochastic Rewards: Provable Better Bound via Adversarial Reinforcement Learning
  17. ICML 2024OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shift
  18. ICML 2024Position: Exploring the Robustness of Pipeline-Parallelism-Based Decentralized Training
  19. ICML 2024Precise Accuracy / Robustness Tradeoffs in Regression: Case of General Norms
  20. ICML 2024Prompting is a Double-Edged Sword: Improving Worst-Group Robustness of Foundation Models
  21. ICML 2024Provably Better Explanations with Optimized Aggregation of Feature Attributions
  22. ICML 2024Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback
  23. ICML 2024Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders
  24. ICML 2024RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation
  25. ICML 2024Rethinking Adversarial Robustness in the Context of the Right to be Forgotten
  26. ICML 2024Revealing the Dark Secrets of Extremely Large Kernel ConvNets on Robustness
  27. ICML 2024Revisiting Character-level Adversarial Attacks for Language Models
  28. ICML 2024Riemannian Accelerated Zeroth-order Algorithm: Improved Robustness and Lower Query Complexity
  29. ICML 2024Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
  30. ICML 2024Robust Stable Spiking Neural Networks
  31. ICML 2024Robust Universal Adversarial Perturbations
  32. ICML 2024Robustness of Deep Learning for Accelerated MRI: Benefits of Diverse Training Data
  33. ICML 2024Robustness of Nonlinear Representation Learning
  34. ICML 2024Roping in Uncertainty: Robustness and Regularization in Markov Games
  35. ICML 2024SignSGD with Federated Defense: Harnessing Adversarial Attacks through Gradient Sign Decoding
  36. ICML 2024The Perception-Robustness Tradeoff in Deterministic Image Restoration
  37. ICML 2024The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks
  38. ICML 2024Towards Efficient Training and Evaluation of Robust Models against $l_0$ Bounded Adversarial Perturbations
  39. ICML 2024Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error
  40. ICML 2024Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption
  41. ICML 2024Triadic-OCD: Asynchronous Online Change Detection with Provable Robustness, Optimality, and Convergence
  42. ICML 2024Two Heads are Actually Better than One: Towards Better Adversarial Robustness via Transduction and Rejection
  43. ICML 2024Two Tales of Single-Phase Contrastive Hebbian Learning
  44. ICML 2024Uniformly Stable Algorithms for Adversarial Training and Beyond
  45. ICML 2024VNN: Verification-Friendly Neural Networks with Hard Robustness Guarantees
  46. ICML 2024WAVES: Benchmarking the Robustness of Image Watermarks
  47. NeurIPS 2024A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive Delays
  48. NeurIPS 2024A Non-parametric Direct Learning Approach to Heterogeneous Treatment Effect Estimation under Unmeasured Confounding
  49. NeurIPS 2024A Sober Look at the Robustness of CLIPs to Spurious Features
  50. NeurIPS 2024A StrongREJECT for Empty Jailbreaks

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