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 11 / 26 页

  1. ICML 2025On the Tension between Byzantine Robustness and No-Attack Accuracy in Distributed Learning
  2. ICML 2025One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy
  3. ICML 2025Optimal Fair Learning Robust to Adversarial Distribution Shift
  4. ICML 2025Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach
  5. ICML 2025Phase and Amplitude-aware Prompting for Enhancing Adversarial Robustness
  6. ICML 2025Pixel-level Certified Explanations via Randomized Smoothing
  7. ICML 2025Pixel2Feature Attack (P2FA): Rethinking the Perturbed Space to Enhance Adversarial Transferability
  8. ICML 2025Position: Certified Robustness Does Not (Yet) Imply Model Security
  9. ICML 2025Probably Approximately Global Robustness Certification
  10. ICML 2025Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing
  11. ICML 2025Quadratic Upper Bound for Boosting Robustness
  12. ICML 2025REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective
  13. ICML 2025Robust Automatic Modulation Classification with Fuzzy Regularization
  14. ICML 2025RobustLight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal Control
  15. ICML 2025RobustZero: Enhancing MuZero Reinforcement Learning Robustness to State Perturbations
  16. ICML 2025ROME is Forged in Adversity: Robust Distilled Datasets via Information Bottleneck
  17. ICML 2025Sample-specific Noise Injection for Diffusion-based Adversarial Purification
  18. ICML 2025Scaling Trends in Language Model Robustness
  19. ICML 2025Self-Consuming Generative Models with Adversarially Curated Data
  20. ICML 2025Self-supervised Adversarial Purification for Graph Neural Networks
  21. ICML 2025SGD Jittering: A Training Strategy for Robust and Accurate Model-Based Architectures
  22. ICML 2025Splitting & Integrating: Out-of-Distribution Detection via Adversarial Gradient Attribution
  23. ICML 2025Statistical Hypothesis Testing for Auditing Robustness in Language Models
  24. ICML 2025Towards Robust Influence Functions with Flat Validation Minima
  25. ICML 2025Towards Robustness and Explainability of Automatic Algorithm Selection
  26. ICML 2025TtBA: Two-third Bridge Approach for Decision-Based Adversarial Attack
  27. ICML 2025Understanding Model Ensemble in Transferable Adversarial Attack
  28. ICML 2025Unified Breakdown Analysis for Byzantine Robust Gossip
  29. ICML 2025Universal Neural Optimal Transport
  30. ICML 2025Unveiling AI's Blind Spots: An Oracle for In-Domain, Out-of-Domain, and Adversarial Errors
  31. ICML 2025Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning
  32. ICML 2025When and How Does CLIP Enable Domain and Compositional Generalization?
  33. ICML 2025X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
  34. NeurIPS 2025A data and task-constrained mechanistic model of the mouse outer retina shows robustness to contrast variations
  35. NeurIPS 2025A Near-optimal, Scalable and Parallelizable Framework for Stochastic Bandits Robust to Adversarial Corruptions and Beyond
  36. NeurIPS 2025A Unified Approach to Submodular Maximization Under Noise
  37. NeurIPS 2025Accelerated Vertical Federated Adversarial Learning through Decoupling Layer-Wise Dependencies
  38. NeurIPS 2025AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness
  39. NeurIPS 2025Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
  40. NeurIPS 2025Adv-SSL: Adversarial Self-Supervised Representation Learning with Theoretical Guarantees
  41. NeurIPS 2025Adversarial Diffusion for Robust Reinforcement Learning
  42. NeurIPS 2025Adversarial generalization of unfolding (model-based) networks
  43. NeurIPS 2025Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text
  44. NeurIPS 2025Adversarial Robustness of Nonparametric Regression
  45. NeurIPS 2025Adversary Aware Optimization for Robust Defense
  46. NeurIPS 2025AdvPrefix: An Objective for Nuanced LLM Jailbreaks
  47. NeurIPS 2025Alias-Free ViT: Fractional Shift Invariance via Linear Attention
  48. NeurIPS 2025An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction
  49. NeurIPS 2025AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant Adversarial Patches
  50. NeurIPS 2025Attention! Your Vision Language Model Could Be Maliciously Manipulated

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