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 19 / 26 页

  1. NeurIPS 2024Fight Back Against Jailbreaking via Prompt Adversarial Tuning
  2. NeurIPS 2024Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients
  3. NeurIPS 2024Full-Distance Evasion of Pedestrian Detectors in the Physical World
  4. NeurIPS 2024GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning
  5. NeurIPS 2024Generate Universal Adversarial Perturbations for Few-Shot Learning
  6. NeurIPS 2024GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models
  7. NeurIPS 2024GuardT2I: Defending Text-to-Image Models from Adversarial Prompts
  8. NeurIPS 2024High-dimensional (Group) Adversarial Training in Linear Regression
  9. NeurIPS 2024If You Want to Be Robust, Be Wary of Initialization
  10. NeurIPS 2024Improved Generation of Adversarial Examples Against Safety-aligned LLMs
  11. NeurIPS 2024Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation
  12. NeurIPS 2024Improving Alignment and Robustness with Circuit Breakers
  13. NeurIPS 2024Improving Robustness of 3D Point Cloud Recognition from a Fourier Perspective
  14. NeurIPS 2024Improving robustness to corruptions with multiplicative weight perturbations
  15. NeurIPS 2024Improving Subgroup Robustness via Data Selection
  16. NeurIPS 2024Intrinsic Robustness of Prophet Inequality to Strategic Reward Signaling
  17. NeurIPS 2024Is O(log N) practical? Near-Equivalence Between Delay Robustness and Bounded Regret in Bandits and RL
  18. NeurIPS 2024JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
  19. NeurIPS 2024Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise
  20. NeurIPS 2024Learning Bregman Divergences with Application to Robustness
  21. NeurIPS 2024Learning from Uncertain Data: From Possible Worlds to Possible Models
  22. NeurIPS 2024Learning-Augmented Algorithms for the Bahncard Problem
  23. NeurIPS 2024MALT Powers Up Adversarial Attacks
  24. NeurIPS 2024Mind the Graph When Balancing Data for Fairness or Robustness
  25. NeurIPS 2024Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
  26. NeurIPS 2024Mixture of Adversarial LoRAs: Boosting Robust Generalization in Meta-Tuning
  27. NeurIPS 2024Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs
  28. NeurIPS 2024No Free Lunch Theorem and Black-Box Complexity Analysis for Adversarial Optimisation
  29. NeurIPS 2024No-Regret M${}^{\natural}$-Concave Function Maximization: Stochastic Bandit Algorithms and NP-Hardness of Adversarial Full-Information Setting
  30. NeurIPS 2024On the Adversarial Robustness of Benjamini Hochberg
  31. NeurIPS 2024On the Robustness of Spectral Algorithms for Semirandom Stochastic Block Models
  32. NeurIPS 2024On the Scalability of Certified Adversarial Robustness with Generated Data
  33. NeurIPS 2024On the Worst Prompt Performance of Large Language Models
  34. NeurIPS 2024Online Composite Optimization Between Stochastic and Adversarial Environments
  35. NeurIPS 2024Optimal Classification under Performative Distribution Shift
  36. NeurIPS 2024Probabilistic Conformal Distillation for Enhancing Missing Modality Robustness
  37. NeurIPS 2024Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models
  38. NeurIPS 2024ProTransformer: Robustify Transformers via Plug-and-Play Paradigm
  39. NeurIPS 2024Query-Based Adversarial Prompt Generation
  40. NeurIPS 2024Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
  41. NeurIPS 2024RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations for Universal Robustness
  42. NeurIPS 2024Rapid Plug-in Defenders
  43. NeurIPS 2024Reconstruct and Match: Out-of-Distribution Robustness via Topological Homogeneity
  44. NeurIPS 2024REDUCR: Robust Data Downsampling using Class Priority Reweighting
  45. NeurIPS 2024Relational Verification Leaps Forward with RABBit
  46. NeurIPS 2024Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
  47. NeurIPS 2024Rethinking LLM Memorization through the Lens of Adversarial Compression
  48. NeurIPS 2024ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization
  49. NeurIPS 2024Robust Graph Neural Networks via Unbiased Aggregation
  50. NeurIPS 2024Robust Neural Contextual Bandit against Adversarial Corruptions

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