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 316 篇，第 4 / 7 页

  1. ICML 2026Benign Overfitting in Adversarial Training for Vision Transformers
  2. ICML 2026Bias in Zeroth-Order Normal Estimation for Decision-Based Attacks
  3. ICML 2026BiRQA: Bidirectional Robust Quality Assessment for Images
  4. ICML 2026BOCLOAK: Optimal Transport-Guided Adversarial Attacks on Graph Neural Network-Based Bot Detection
  5. ICML 2026Budget-Efficient Attacks and Robustness Training for Cooperative MARL
  6. ICML 2026Bulk-Calibrated Credal Ambiguity Sets: Fast, Tractable Decision Making under Out-of-Sample Contamination
  7. ICML 2026Calibrating Uncertainty for Zero-Shot Adversarial CLIP
  8. ICML 2026CaliDist: Calibrating Large Language Models via Behavioral Robustness to Distraction
  9. ICML 2026Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing
  10. ICML 2026Certifying Graph Neural Networks Against Label and Structure Poisoning
  11. ICML 2026Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP
  12. ICML 2026CORE: Context-Robust Remasking for Diffusion Language Models
  13. ICML 2026Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates
  14. ICML 2026DART: Distribution-Aware Adaptive Relational Transfer for Adversarial Attacks against Closed-Source MLLMs
  15. ICML 2026DDGA: Dirichlet Distributional Gradient Aggregation for Transferable Vision-Language Adversarial Attacks
  16. ICML 2026DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers
  17. ICML 2026Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment
  18. ICML 2026Distributionally Robust Markov Games with Average Reward
  19. ICML 2026Does a Hybrid Space-Aware Randomized Defense Improve Empirical and Certified Adversarial Robustness?
  20. ICML 2026Dual-branch Robust Unlearnable Examples
  21. ICML 2026Enhanced Latent-Space Adversarial Training for Super-Resolution
  22. ICML 2026Feature Collapse Under Corruption: An Entropy Perspective on Robust Neural Networks
  23. ICML 2026Fingerprinting Pre-trained Encoders under Arbitrary Downstream Fine-Tuning via Adversarial Shifting
  24. ICML 2026From Internal Diagnosis to External Auditing: A VLM-Driven Paradigm for Data-Free Online Backdoor Defense
  25. ICML 2026Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation Recognition
  26. ICML 2026Harnessing Non-Adversarial Robustness in Large Language Models
  27. ICML 2026Hearing Without Noticing? Attention-Aware Stealthy Black-Box Adversarial Audio Attacks
  28. ICML 2026High-Dimensional Sensitivity Analysis for Genomic Studies: An Adversarial Framework for Learning Worst-Case Latent Confounders
  29. ICML 2026Higher-Order Certified Robustness for Regression
  30. ICML 2026Identifiable Smooth Conjugacy Learning via Adversarial Orthogonality
  31. ICML 2026Improving Adversarial Robustness of Attribution via Implicit Regularization
  32. ICML 2026Improving the Robustness-Utility Trade-off in Decentralized Learning over Sparse Networks
  33. ICML 2026Improving the Sensitivity of Backdoor Detectors via Class Subspace Orthogonalization
  34. ICML 2026Learning to Emulate Chaos: Adversarial Optimal Transport Regularization
  35. ICML 2026Localize and Neutralize: Gradient-Guided Token Suppression Against Visual Prompt Injection Attack
  36. ICML 2026Logit Distance Bounds Representational Similarity
  37. ICML 2026MaMa: A Game-Theoretic Approach for Designing Safe Agentic Systems
  38. ICML 2026MEDUSA: Motion Elimination in Diffusion Using Spectral Attack
  39. ICML 2026Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust?
  40. ICML 2026MoCo-EA: Exploiting Adversarial Mode Connectivity for Efficient Evolutionary Attacks
  41. ICML 2026Near-Minimax Multi-Objective RL under Predictable Adversarial Preferences and Preference-Free Exploration in Linear MDPs
  42. ICML 2026Non-Parametric Probabilistic Robustness: A Conservative Risk Estimator under Unknown Perturbation Distributions
  43. ICML 2026On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs
  44. ICML 2026On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
  45. ICML 2026On the Existence of Consistent Adversarial Attacks in High-Dimensional Linear Classification
  46. ICML 2026On the Robustness of Langevin Dynamics to Score Function Error
  47. ICML 2026Optimal Attention Temperature Improves the Robustness of In-Context Learning under Distribution Shift in High Dimensions
  48. ICML 2026Posterior Mismatch Matters: Adversarial Training for Long-Tailed Robustness
  49. ICML 2026Proactive Defense Benchmark against Deepfake Generation
  50. ICML 2026Probabilistic Robustness Certificates against Adversarial Attacks

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