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 331 篇，第 5 / 7 页

  1. ICLR 2024Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks
  2. ICLR 2024BRUSLEATTACK: A QUERY-EFFICIENT SCORE- BASED BLACK-BOX SPARSE ADVERSARIAL ATTACK
  3. ICLR 2024Certified Adversarial Robustness for Rate Encoded Spiking Neural Networks
  4. ICLR 2024COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits
  5. ICLR 2024Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training
  6. ICLR 2024Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit
  7. ICLR 2024DAFA: Distance-Aware Fair Adversarial Training
  8. ICLR 2024Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Search
  9. ICLR 2024Doubly Robust Instance-Reweighted Adversarial Training
  10. ICLR 2024DP-SGD Without Clipping: The Lipschitz Neural Network Way
  11. ICLR 2024DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness
  12. ICLR 2024Efficient local linearity regularization to overcome catastrophic overfitting
  13. ICLR 2024Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches
  14. ICLR 2024Evaluating the Zero-shot Robustness of Instruction-tuned Language Models
  15. ICLR 2024Expressive Losses for Verified Robustness via Convex Combinations
  16. ICLR 2024Expressivity of ReLU-Networks under Convex Relaxations
  17. ICLR 2024Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
  18. ICLR 2024GNNCert: Deterministic Certification of Graph Neural Networks against Adversarial Perturbations
  19. ICLR 2024Incremental Randomized Smoothing Certification
  20. ICLR 2024Input-gradient space particle inference for neural network ensembles
  21. ICLR 2024Interpreting Robustness Proofs of Deep Neural Networks
  22. ICLR 2024IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks
  23. ICLR 2024Label-Noise Robust Diffusion Models
  24. ICLR 2024Large Language Models Are Not Robust Multiple Choice Selectors
  25. ICLR 2024Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds
  26. ICLR 2024LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
  27. ICLR 2024Mitigating Emergent Robustness Degradation while Scaling Graph Learning
  28. ICLR 2024Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing
  29. ICLR 2024On Adversarial Training without Perturbing all Examples
  30. ICLR 2024On the Vulnerability of Adversarially Trained Models Against Two-faced Attacks
  31. ICLR 2024Optimal transport based adversarial patch to leverage large scale attack transferability
  32. ICLR 2024Out-Of-Domain Unlabeled Data Improves Generalization
  33. ICLR 2024Provably Robust Conformal Prediction with Improved Efficiency
  34. ICLR 2024PubDef: Defending Against Transfer Attacks From Public Models
  35. ICLR 2024Pushing Boundaries: Mixup's Influence on Neural Collapse
  36. ICLR 2024Quantifying and Enhancing Multi-modal Robustness with Modality Preference
  37. ICLR 2024Rethinking Model Ensemble in Transfer-based Adversarial Attacks
  38. ICLR 2024Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula
  39. ICLR 2024Robust Classification via Regression for Learning with Noisy Labels
  40. ICLR 2024Robust NAS under adversarial training: benchmark, theory, and beyond
  41. ICLR 2024Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
  42. ICLR 2024SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer
  43. ICLR 2024Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
  44. ICLR 2024The Effectiveness of Random Forgetting for Robust Generalization
  45. ICLR 2024Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach
  46. ICLR 2024Theoretical Understanding of Learning from Adversarial Perturbations
  47. ICLR 2024Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback
  48. ICLR 2024Towards Robust Out-of-Distribution Generalization Bounds via Sharpness
  49. ICLR 2024Understanding Certified Training with Interval Bound Propagation
  50. ICLR 2024Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift

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