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 85 篇，第 2 / 2 页

51. ICML 2025On the Learnability of Distribution Classes with Adaptive Adversaries
52. ICML 2025On the Local Complexity of Linear Regions in Deep ReLU Networks
53. ICML 2025On the Tension between Byzantine Robustness and No-Attack Accuracy in Distributed Learning
54. ICML 2025One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy
55. ICML 2025Optimal Fair Learning Robust to Adversarial Distribution Shift
56. ICML 2025Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach
57. ICML 2025Phase and Amplitude-aware Prompting for Enhancing Adversarial Robustness
58. ICML 2025Pixel-level Certified Explanations via Randomized Smoothing
59. ICML 2025Pixel2Feature Attack (P2FA): Rethinking the Perturbed Space to Enhance Adversarial Transferability
60. ICML 2025Position: Certified Robustness Does Not (Yet) Imply Model Security
61. ICML 2025Probably Approximately Global Robustness Certification
62. ICML 2025Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing
63. ICML 2025Quadratic Upper Bound for Boosting Robustness
64. ICML 2025REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective
65. ICML 2025Robust Automatic Modulation Classification with Fuzzy Regularization
66. ICML 2025RobustLight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal Control
67. ICML 2025RobustZero: Enhancing MuZero Reinforcement Learning Robustness to State Perturbations
68. ICML 2025ROME is Forged in Adversity: Robust Distilled Datasets via Information Bottleneck
69. ICML 2025Sample-specific Noise Injection for Diffusion-based Adversarial Purification
70. ICML 2025Scaling Trends in Language Model Robustness
71. ICML 2025Self-Consuming Generative Models with Adversarially Curated Data
72. ICML 2025Self-supervised Adversarial Purification for Graph Neural Networks
73. ICML 2025SGD Jittering: A Training Strategy for Robust and Accurate Model-Based Architectures
74. ICML 2025Splitting & Integrating: Out-of-Distribution Detection via Adversarial Gradient Attribution
75. ICML 2025Statistical Hypothesis Testing for Auditing Robustness in Language Models
76. ICML 2025Towards Robust Influence Functions with Flat Validation Minima
77. ICML 2025Towards Robustness and Explainability of Automatic Algorithm Selection
78. ICML 2025TtBA: Two-third Bridge Approach for Decision-Based Adversarial Attack
79. ICML 2025Understanding Model Ensemble in Transferable Adversarial Attack
80. ICML 2025Unified Breakdown Analysis for Byzantine Robust Gossip
81. ICML 2025Universal Neural Optimal Transport
82. ICML 2025Unveiling AI's Blind Spots: An Oracle for In-Domain, Out-of-Domain, and Adversarial Errors
83. ICML 2025Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning
84. ICML 2025When and How Does CLIP Enable Domain and Compositional Generalization?
85. ICML 2025X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP

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。