对抗鲁棒论文趋势 2023–2026

主要结论

• 对抗鲁棒论文从 2023 年的 313 篇增长到 2026 年的 317 篇，三年间扩大到约 1.0 倍。
• NeurIPS 是发对抗鲁棒论文最多的会议，2023–2026 年共 422 篇，占四个会议总量的 33%。
• 交叉方向里涨得最快的是对齐与安全：同时属于两个主题的论文从 2023 年的 13 篇增至 2026 年的 56 篇。
• 在「安全与可信」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的水印是 9.3 倍，对抗鲁棒是 1.0 倍。

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

• NeurIPS 2026A Little Robustness Is All You Need: Leveraging Predictions for Contextual Optimization
• ICML 2026Bias in Zeroth-Order Normal Estimation for Decision-Based Attacks
• ICLR 2026CERTIFIED VS. EMPIRICAL ADVERSARIAL ROBUSTNESS VIA HYBRID CONVOLUTIONS WITH ATTENTION STOCHASTICITY
• CVPR 2026A Combination of Noise and Bilateral Filters Achieve Supralinear and
• NeurIPS 2025A Unified Approach to Submodular Maximization Under Noise
• ICML 2025Adversarial Perturbations Are Formed by Iteratively Learning Linear Combinations of the Right Singular Vectors of the Adversarial Jacobian
• ICLR 2025$\sigma$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples
• CVPR 2025A Unified, Resilient, and Explainable Adversarial Patch Detector
• NeurIPS 2024A StrongREJECT for Empty Jailbreaks
• ICML 2024Adversarial Attacks on Combinatorial Multi-Armed Bandits
• ICLR 2024An LLM can Fool Itself: A Prompt-Based Adversarial Attack
• CVPR 2024Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization
• NeurIPS 2023A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)
• ICML 2023A Law of Robustness beyond Isoperimetry
• ICLR 2023A law of adversarial risk, interpolation, and label noise
• CVPR 2023Adversarial Normalization: I Can Visualize Everything (ICE)
• NeurIPS 2026A Regularization-Based Approach to Public Belief State Search for Adversarial Games
• ICML 2026CaliDist: Calibrating Large Language Models via Behavioral Robustness to Distraction
• ICLR 2026Conformal Robustness Control: A New Strategy for Robust Decision
• CVPR 2026A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large

全部对抗鲁棒论文

共 88 篇，第 2 / 2 页

51. ICLR 2025Long-tailed Adversarial Training with Self-Distillation
52. ICLR 2025Measuring Non-Adversarial Reproduction of Training Data in Large Language Models
53. ICLR 2025Minimax Optimal Two-Stage Algorithm For Moment Estimation Under Covariate Shift
54. ICLR 2025MixMax: Distributional Robustness in Function Space via Optimal Data Mixtures
55. ICLR 2025Model-Free Offline Reinforcement Learning with Enhanced Robustness
56. ICLR 2025Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning
57. ICLR 2025Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching
58. ICLR 2025On Minimizing Adversarial Counterfactual Error in Adversarial Reinforcement Learning
59. ICLR 2025Optimizing importance weighting in the presence of sub-population shifts
60. ICLR 2025PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs
61. ICLR 2025Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization
62. ICLR 2025Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning
63. ICLR 2025Provably Safeguarding a Classifier from OOD and Adversarial Samples
64. ICLR 2025Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off
65. ICLR 2025Robust Feature Learning for Multi-Index Models in High Dimensions
66. ICLR 2025Robust LLM safeguarding via refusal feature adversarial training
67. ICLR 2025Robust Representation Consistency Model via Contrastive Denoising
68. ICLR 2025Robust Transfer of Safety-Constrained Reinforcement Learning Agents
69. ICLR 2025Robustness Auditing for Linear Regression: To Singularity and Beyond
70. ICLR 2025Robustness Inspired Graph Backdoor Defense
71. ICLR 2025Robustness Reprogramming for Representation Learning
72. ICLR 2025Selective Unlearning via Representation Erasure Using Domain Adversarial Training
73. ICLR 2025Shh, don't say that! Domain Certification in LLMs
74. ICLR 2025Speech Robust Bench: A Robustness Benchmark For Speech Recognition
75. ICLR 2025Stochastic Bandits Robust to Adversarial Attacks
76. ICLR 2025Strong Preferences Affect the Robustness of Preference Models and Value Alignment
77. ICLR 2025Tailoring Mixup to Data for Calibration
78. ICLR 2025Targeted Attack Improves Protection against Unauthorized Diffusion Customization
79. ICLR 2025TASAR: Transfer-based Attack on Skeletal Action Recognition
80. ICLR 2025Tight Clusters Make Specialized Experts
81. ICLR 2025To Tackle Adversarial Transferability: A Novel Ensemble Training Method with Fourier Transformation
82. ICLR 2025Towards Certification of Uncertainty Calibration under Adversarial Attacks
83. ICLR 2025Towards Scalable Topological Regularizers
84. ICLR 2025Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
85. ICLR 2025Training Robust Ensembles Requires Rethinking Lipschitz Continuity
86. ICLR 2025Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
87. ICLR 2025Verifying Properties of Binary Neural Networks Using Sparse Polynomial Optimization
88. ICLR 2025Zero-cost Proxy for Adversarial Robustness Evaluation

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。