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 422 篇，第 5 / 9 页

  1. NeurIPS 2024Adversarial Environment Design via Regret-Guided Diffusion Models
  2. NeurIPS 2024Adversarial Moment-Matching Distillation of Large Language Models
  3. NeurIPS 2024Adversarial Schrödinger Bridge Matching
  4. NeurIPS 2024Adversarially Robust Decision Transformer
  5. NeurIPS 2024Adversarially Robust Dense-Sparse Tradeoffs via Heavy-Hitters
  6. NeurIPS 2024AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
  7. NeurIPS 2024An Analysis of Robustness of Non-Lipschitz Networks
  8. NeurIPS 2024AudioMarkBench: Benchmarking Robustness of Audio Watermarking
  9. NeurIPS 2024Back to the Continuous Attractor
  10. NeurIPS 2024BAN: Detecting Backdoors Activated by Adversarial Neuron Noise
  11. NeurIPS 2024Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback
  12. NeurIPS 2024Beware of Road Markings: A New Adversarial Patch Attack to Monocular Depth Estimation
  13. NeurIPS 2024Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints
  14. NeurIPS 2024Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift
  15. NeurIPS 2024Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences
  16. NeurIPS 2024Can Models Learn Skill Composition from Examples?
  17. NeurIPS 2024CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense
  18. NeurIPS 2024Certified Adversarial Robustness via Randomized $\alpha$-Smoothing for Regression Models
  19. NeurIPS 2024Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing
  20. NeurIPS 2024Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness
  21. NeurIPS 2024Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data
  22. NeurIPS 2024Constructing Semantics-Aware Adversarial Examples with a Probabilistic Perspective
  23. NeurIPS 2024Cross-Modality Perturbation Synergy Attack for Person Re-identification
  24. NeurIPS 2024DarkSAM: Fooling Segment Anything Model to Segment Nothing
  25. NeurIPS 2024DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain
  26. NeurIPS 2024Decoupled Kullback-Leibler Divergence Loss
  27. NeurIPS 2024Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
  28. NeurIPS 2024DeNetDM: Debiasing by Network Depth Modulation
  29. NeurIPS 2024DeSparsify: Adversarial Attack Against Token Sparsification Mechanisms
  30. NeurIPS 2024Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers
  31. NeurIPS 2024DiffHammer: Rethinking the Robustness of Diffusion-Based Adversarial Purification
  32. NeurIPS 2024Diffusion Models are Certifiably Robust Classifiers
  33. NeurIPS 2024Diffusion-Reward Adversarial Imitation Learning
  34. NeurIPS 2024ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks
  35. NeurIPS 2024Edit Distance Robust Watermarks via Indexing Pseudorandom Codes
  36. NeurIPS 2024Efficient Adversarial Training in LLMs with Continuous Attacks
  37. NeurIPS 2024Elliptical Attention
  38. NeurIPS 2024Elo Uncovered: Robustness and Best Practices in Language Model Evaluation
  39. NeurIPS 2024Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach
  40. NeurIPS 2024Enhancing Robustness of Graph Neural Networks on Social Media with Explainable Inverse Reinforcement Learning
  41. NeurIPS 2024Enhancing Robustness of Last Layer Two-Stage Fair Model Corrections
  42. NeurIPS 2024Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
  43. NeurIPS 2024Exploring Adversarial Robustness of Deep State Space Models
  44. NeurIPS 2024Feature-Level Adversarial Attacks and Ranking Disruption for Visible-Infrared Person Re-identification
  45. NeurIPS 2024FEEL-SNN: Robust Spiking Neural Networks with Frequency Encoding and Evolutionary Leak Factor
  46. NeurIPS 2024Fight Back Against Jailbreaking via Prompt Adversarial Tuning
  47. NeurIPS 2024Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients
  48. NeurIPS 2024Full-Distance Evasion of Pedestrian Detectors in the Physical World
  49. NeurIPS 2024GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning
  50. NeurIPS 2024Generate Universal Adversarial Perturbations for Few-Shot Learning

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