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 13 / 26 页

  1. NeurIPS 2025No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!
  2. NeurIPS 2025On the Optimality of the Median-of-Means Estimator under Adversarial Contamination
  3. NeurIPS 2025On the Robustness of Transformers against Context Hijacking for Linear Classification
  4. NeurIPS 2025On the Robustness of Verbal Confidence of LLMs in Adversarial Attacks
  5. NeurIPS 2025Optimal Control for Transformer Architectures: Enhancing Generalization, Robustness and Efficiency
  6. NeurIPS 2025OSTAR: Optimized Statistical Text-classifier with Adversarial Resistance
  7. NeurIPS 2025Parameter-free Algorithms for the Stochastically Extended Adversarial Model
  8. NeurIPS 2025PCA++: How Uniformity Induces Robustness to Background Noise in Contrastive Learning
  9. NeurIPS 2025Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback
  10. NeurIPS 2025ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search
  11. NeurIPS 2025Remarkable Robustness of LLMs: Stages of Inference?
  12. NeurIPS 2025Reverse Engineering Human Preferences with Reinforcement Learning
  13. NeurIPS 2025Robust Equilibria in Continuous Games: From Strategic to Dynamic Robustness
  14. NeurIPS 2025Robust learning of halfspaces under log-concave marginals
  15. NeurIPS 2025Robust Satisficing Gaussian Process Bandits Under Adversarial Attacks
  16. NeurIPS 2025Robust SuperAlignment: Weak-to-Strong Robustness Generalization for Vision-Language Models
  17. NeurIPS 2025Robustifying Learning-Augmented Caching Efficiently without Compromising 1-Consistency
  18. NeurIPS 2025Robustness in Both Domains: CLIP Needs a Robust Text Encoder
  19. NeurIPS 2025Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning
  20. NeurIPS 2025Scalable Neural Network Geometric Robustness Validation via Hölder Optimisation
  21. NeurIPS 2025Scaling Data-Driven Probabilistic Robustness Analysis for Semantic Segmentation Neural Networks
  22. NeurIPS 2025SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations
  23. NeurIPS 2025Self-Refining Language Model Anonymizers via Adversarial Distillation
  24. NeurIPS 2025Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence
  25. NeurIPS 2025Statistical Analysis of an Adversarial Bayesian Weak Supervision Method
  26. NeurIPS 2025Stochastic Shortest Path with Sparse Adversarial Costs
  27. NeurIPS 2025Taming Adversarial Constraints in CMDPs
  28. NeurIPS 2025The Cost of Compression: Tight Quadratic Black-Box Attacks on Sketches for $\ell_2$ Norm Estimation
  29. NeurIPS 2025The Cost of Robustness: Tighter Bounds on Parameter Complexity for Robust Memorization in ReLU Nets
  30. NeurIPS 2025The Fluorescent Veil: A Stealthy and Effective Physical Adversarial Patch Against Traffic Sign Recognition
  31. NeurIPS 2025The Good, the Bad and the Ugly: Meta-Analysis of Watermarks, Transferable Attacks and Adversarial Defenses
  32. NeurIPS 2025The Impact of Coreset Selection on Spurious Correlations and Group Robustness
  33. NeurIPS 2025The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels
  34. NeurIPS 2025The Right to Red-Team: Adversarial AI Literacy as a Civic Imperative in K-12 Education
  35. NeurIPS 2025The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples
  36. NeurIPS 2025Theoretical Guarantees for the Retention of Strict Nash Equilibria by Coevolutionary Algorithms
  37. NeurIPS 2025Transstratal Adversarial Attack: Compromising Multi-Layered Defenses in Text-to-Image Models
  38. NeurIPS 2025Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits
  39. NeurIPS 2025Understanding and Improving Fast Adversarial Training against $l_0$ Bounded Perturbations
  40. NeurIPS 2025Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2
  41. NeurIPS 2025Vulnerable Data-Aware Adversarial Training
  42. NeurIPS 2025When Are Concepts Erased From Diffusion Models?
  43. NeurIPS 2025When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspective
  44. CVPR 20241-Lipschitz Layers Compared: Memory Speed and Certifiable Robustness
  45. CVPR 2024A Bayesian Approach to OOD Robustness in Image Classification
  46. CVPR 2024ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models
  47. CVPR 2024Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Driving
  48. CVPR 2024Adversarial Distillation Based on Slack Matching and Attribution Region Alignment
  49. CVPR 2024Adversarial Score Distillation: When score distillation meets GAN
  50. CVPR 2024ASAM: Boosting Segment Anything Model with Adversarial Tuning

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