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 422 篇，第 9 / 9 页

  1. NeurIPS 2023Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples
  2. NeurIPS 2023Spatial-frequency channels, shape bias, and adversarial robustness
  3. NeurIPS 2023Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases
  4. NeurIPS 2023Stable Diffusion is Unstable
  5. NeurIPS 2023Static and Sequential Malicious Attacks in the Context of Selective Forgetting
  6. NeurIPS 2023Strong and Precise Modulation of Human Percepts via Robustified ANNs
  7. NeurIPS 2023Temporal Robustness against Data poisoning
  8. NeurIPS 2023The Adversarial Consistency of Surrogate Risks for Binary Classification
  9. NeurIPS 2023The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks
  10. NeurIPS 2023Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly
  11. NeurIPS 2023Towards Higher Ranks via Adversarial Weight Pruning
  12. NeurIPS 2023Towards Last-layer Retraining for Group Robustness with Fewer Annotations
  13. NeurIPS 2023Training on Foveated Images Improves Robustness to Adversarial Attacks
  14. NeurIPS 2023Transferable Adversarial Robustness for Categorical Data via Universal Robust Embeddings
  15. NeurIPS 2023Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships
  16. NeurIPS 2023Understanding and Improving Ensemble Adversarial Defense
  17. NeurIPS 2023UniT: A Unified Look at Certified Robust Training against Text Adversarial Perturbation
  18. NeurIPS 2023Unlocking Deterministic Robustness Certification on ImageNet
  19. NeurIPS 2023VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models
  20. NeurIPS 2023Wasserstein distributional robustness of neural networks
  21. NeurIPS 2023What Can We Learn from Unlearnable Datasets?
  22. NeurIPS 2023What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners?

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