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 327 篇，第 5 / 7 页

  1. ICML 2025Sample-specific Noise Injection for Diffusion-based Adversarial Purification
  2. ICML 2025Scaling Trends in Language Model Robustness
  3. ICML 2025Self-Consuming Generative Models with Adversarially Curated Data
  4. ICML 2025Self-supervised Adversarial Purification for Graph Neural Networks
  5. ICML 2025SGD Jittering: A Training Strategy for Robust and Accurate Model-Based Architectures
  6. ICML 2025Splitting & Integrating: Out-of-Distribution Detection via Adversarial Gradient Attribution
  7. ICML 2025Statistical Hypothesis Testing for Auditing Robustness in Language Models
  8. ICML 2025Towards Robust Influence Functions with Flat Validation Minima
  9. ICML 2025Towards Robustness and Explainability of Automatic Algorithm Selection
  10. ICML 2025TtBA: Two-third Bridge Approach for Decision-Based Adversarial Attack
  11. ICML 2025Understanding Model Ensemble in Transferable Adversarial Attack
  12. ICML 2025Unified Breakdown Analysis for Byzantine Robust Gossip
  13. ICML 2025Universal Neural Optimal Transport
  14. ICML 2025Unveiling AI's Blind Spots: An Oracle for In-Domain, Out-of-Domain, and Adversarial Errors
  15. ICML 2025Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning
  16. ICML 2025When and How Does CLIP Enable Domain and Compositional Generalization?
  17. ICML 2025X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
  18. NeurIPS 2025A data and task-constrained mechanistic model of the mouse outer retina shows robustness to contrast variations
  19. NeurIPS 2025A Near-optimal, Scalable and Parallelizable Framework for Stochastic Bandits Robust to Adversarial Corruptions and Beyond
  20. NeurIPS 2025A Unified Approach to Submodular Maximization Under Noise
  21. NeurIPS 2025Accelerated Vertical Federated Adversarial Learning through Decoupling Layer-Wise Dependencies
  22. NeurIPS 2025AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness
  23. NeurIPS 2025Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
  24. NeurIPS 2025Adv-SSL: Adversarial Self-Supervised Representation Learning with Theoretical Guarantees
  25. NeurIPS 2025Adversarial Diffusion for Robust Reinforcement Learning
  26. NeurIPS 2025Adversarial generalization of unfolding (model-based) networks
  27. NeurIPS 2025Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text
  28. NeurIPS 2025Adversarial Robustness of Nonparametric Regression
  29. NeurIPS 2025Adversary Aware Optimization for Robust Defense
  30. NeurIPS 2025AdvPrefix: An Objective for Nuanced LLM Jailbreaks
  31. NeurIPS 2025Alias-Free ViT: Fractional Shift Invariance via Linear Attention
  32. NeurIPS 2025An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction
  33. NeurIPS 2025AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant Adversarial Patches
  34. NeurIPS 2025Attention! Your Vision Language Model Could Be Maliciously Manipulated
  35. NeurIPS 2025AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration
  36. NeurIPS 2025Backdoor Mitigation via Invertible Pruning Masks
  37. NeurIPS 2025BAM-ICL: Causal Hijacking In-Context Learning with Budgeted Adversarial Manipulation
  38. NeurIPS 2025Best-of-N Jailbreaking
  39. NeurIPS 2025Better Language Model Inversion by Compactly Representing Next-Token Distributions
  40. NeurIPS 2025Beyond $\tilde{O}(\sqrt{T})$ Constraint Violation for Online Convex Optimization with Adversarial Constraints
  41. NeurIPS 2025Bits Leaked per Query: Information-Theoretic Bounds for Adversarial Attacks on LLMs
  42. NeurIPS 2025Boosting Adversarial Transferability with Spatial Adversarial Alignment
  43. NeurIPS 2025Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness
  44. NeurIPS 2025Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations
  45. NeurIPS 2025CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs
  46. NeurIPS 2025Certifying Deep Network Risks and Individual Predictions with PAC-Bayes Loss via Localized Priors
  47. NeurIPS 2025CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning
  48. NeurIPS 2025Conformal Prediction under Lévy-Prokhorov Distribution Shifts: Robustness to Local and Global Perturbations
  49. NeurIPS 2025Data Selection Matters: Towards Robust Instruction Tuning of Large Multimodal Models
  50. NeurIPS 2025DenoiseRotator: Enhance Pruning Robustness for LLMs via Importance Concentration

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