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 331 篇，第 4 / 7 页

  1. ICLR 2025Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching
  2. ICLR 2025On Minimizing Adversarial Counterfactual Error in Adversarial Reinforcement Learning
  3. ICLR 2025Optimizing importance weighting in the presence of sub-population shifts
  4. ICLR 2025PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs
  5. ICLR 2025Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization
  6. ICLR 2025Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning
  7. ICLR 2025Provably Safeguarding a Classifier from OOD and Adversarial Samples
  8. ICLR 2025Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off
  9. ICLR 2025Robust Feature Learning for Multi-Index Models in High Dimensions
  10. ICLR 2025Robust LLM safeguarding via refusal feature adversarial training
  11. ICLR 2025Robust Representation Consistency Model via Contrastive Denoising
  12. ICLR 2025Robust Transfer of Safety-Constrained Reinforcement Learning Agents
  13. ICLR 2025Robustness Auditing for Linear Regression: To Singularity and Beyond
  14. ICLR 2025Robustness Inspired Graph Backdoor Defense
  15. ICLR 2025Robustness Reprogramming for Representation Learning
  16. ICLR 2025Selective Unlearning via Representation Erasure Using Domain Adversarial Training
  17. ICLR 2025Shh, don't say that! Domain Certification in LLMs
  18. ICLR 2025Speech Robust Bench: A Robustness Benchmark For Speech Recognition
  19. ICLR 2025Stochastic Bandits Robust to Adversarial Attacks
  20. ICLR 2025Strong Preferences Affect the Robustness of Preference Models and Value Alignment
  21. ICLR 2025Tailoring Mixup to Data for Calibration
  22. ICLR 2025Targeted Attack Improves Protection against Unauthorized Diffusion Customization
  23. ICLR 2025TASAR: Transfer-based Attack on Skeletal Action Recognition
  24. ICLR 2025Tight Clusters Make Specialized Experts
  25. ICLR 2025To Tackle Adversarial Transferability: A Novel Ensemble Training Method with Fourier Transformation
  26. ICLR 2025Towards Certification of Uncertainty Calibration under Adversarial Attacks
  27. ICLR 2025Towards Scalable Topological Regularizers
  28. ICLR 2025Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
  29. ICLR 2025Training Robust Ensembles Requires Rethinking Lipschitz Continuity
  30. ICLR 2025Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
  31. ICLR 2025Verifying Properties of Binary Neural Networks Using Sparse Polynomial Optimization
  32. ICLR 2025Zero-cost Proxy for Adversarial Robustness Evaluation
  33. ICLR 2024A Recipe for Improved Certifiable Robustness
  34. ICLR 2024A ROBUST DIFFERENTIAL NEURAL ODE OPTIMIZER
  35. ICLR 2024A Sublinear Adversarial Training Algorithm
  36. ICLR 2024Adversarial Attacks on Fairness of Graph Neural Networks
  37. ICLR 2024Adversarial AutoMixup
  38. ICLR 2024Adversarial Feature Map Pruning for Backdoor
  39. ICLR 2024Adversarial Imitation Learning via Boosting
  40. ICLR 2024Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization
  41. ICLR 2024Adversarial Training Should Be Cast as a Non-Zero-Sum Game
  42. ICLR 2024An Efficient Tester-Learner for Halfspaces
  43. ICLR 2024An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language Models
  44. ICLR 2024An LLM can Fool Itself: A Prompt-Based Adversarial Attack
  45. ICLR 2024Analyzing and Improving Optimal-Transport-based Adversarial Networks
  46. ICLR 2024Annealing Self-Distillation Rectification Improves Adversarial Training
  47. ICLR 2024AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
  48. ICLR 2024AutoLoRa: An Automated Robust Fine-Tuning Framework
  49. ICLR 2024Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations
  50. ICLR 2024Boosting the Adversarial Robustness of Graph Neural Networks: An OOD 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