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 1,290 篇，第 2 / 26 页

51. ICLR 2026AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models
52. ICLR 2026Adversarial Attacks Already Tell the Answer: Directional Bias-Guided Test-time Defense for Vision-Language Models
53. ICLR 2026Adversarial Déjà Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks
54. ICLR 2026Adversarially Pretrained Transformers may be Universally Robust In-Context Learners
55. ICLR 2026AEGIS: Adversarial Target–Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models
56. ICLR 2026Are Deep Speech Denoising Models Robust to Adversarial Noise?
57. ICLR 2026Are Reasoning LLMs Robust to Interventions on their Chain-of-Thought?
58. ICLR 2026Bandit Learning in Matching Markets Robust to Adversarial Corruptions
59. ICLR 2026Byzantine-Robust Federated Learning with Learnable Aggregation Weights
60. ICLR 2026CERTIFIED VS. EMPIRICAL ADVERSARIAL ROBUSTNESS VIA HYBRID CONVOLUTIONS WITH ATTENTION STOCHASTICITY
61. ICLR 2026Concept-based Adversarial Attack: a Probabilistic Perspective
62. ICLR 2026Conformal Robustness Control: A New Strategy for Robust Decision
63. ICLR 2026Constitutional Classifiers++: Production-Grade Defenses against Universal Jailbreaks
64. ICLR 2026CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question Answering
65. ICLR 2026Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
66. ICLR 2026Diffusion & Adversarial Schrödinger Bridges via Iterative Proportional Markovian Fitting
67. ICLR 2026Discrete Latent Features Ablate Adversarial Attack: A Robust Prompt Tuning Framework for VLMs
68. ICLR 2026Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning
69. ICLR 2026DRIFT: Divergent Response in Filtered Transformations for Robust Adversarial Defense
70. ICLR 2026Dropping Just a Handful of Preferences Can Change Top Large Language Model Rankings
71. ICLR 2026Dual Randomized Smoothing: Beyond Global Noise Variance
72. ICLR 2026Dual-Space Smoothness for Robust and Balanced LLM Unlearning
73. ICLR 2026Efficient Adversarial Attacks on High-dimensional Offline Bandits
74. ICLR 2026Eliciting Harmful Capabilities by Fine-Tuning on Safeguarded Outputs
75. ICLR 2026EvA: Evolutionary Attacks on Graphs
76. ICLR 2026Exposing and Defending the Achilles' Heel of Video Mixture-of-Experts
77. ICLR 2026f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness
78. ICLR 2026FAME: $\underline{F}$ormal $\underline{A}$bstract $\underline{M}$inimal $\underline{E}$xplanation for neural networks
79. ICLR 2026Feature compression is the root cause of adversarial fragility in neural networks
80. ICLR 2026FERD: Fairness-Enhanced Data-Free Adversarial Robustness Distillation
81. ICLR 2026Fine-Grained Iterative Adversarial Attacks with Limited Computation Budget
82. ICLR 2026GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver
83. ICLR 2026Gauge-invariant representation holonomy
84. ICLR 2026Get RICH or Die Scaling: Profitably Trading Inference Compute for Robustness
85. ICLR 2026Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization
86. ICLR 2026Identifying Robust Neural Pathways: Few-Shot Adversarial Mask Tuning for Vision-Language Models
87. ICLR 2026Jailbreak Transferability Emerges from Shared Representations
88. ICLR 2026Latent Wasserstein Adversarial Imitation Learning
89. ICLR 2026LCA: Local Classifier Alignment for Continual Learning
90. ICLR 2026Learning From Dictionary: Enhancing Robustness of Machine-Generated Text Detection in Zero-Shot Language via Adversarial Training
91. ICLR 2026Learning to Generate Unit Test via Adversarial Reinforcement Learning
92. ICLR 2026LipNeXt: Scaling up Lipschitz-based Certified Robustness to Billion-parameter Models
93. ICLR 2026Minimax Optimal Adversarial Reinforcement Learning
94. ICLR 2026Model Predictive Adversarial Imitation Learning for Planning from Observation
95. ICLR 2026Nasty Adversarial Training: A Probability Sparsity Perspective for Robustness Enhancement
96. ICLR 2026NatADiff: Adversarial Boundary Guidance for Natural Adversarial Diffusion
97. ICLR 2026Near-Optimal Second-Order Guarantees for Model-Based Adversarial Imitation Learning
98. ICLR 2026Nearly Space-Optimal Graph and Hypergraph Sparsification in Insertion-Only Data Streams
99. ICLR 2026Noise Tolerance of Distributionally Robust Learning
100. ICLR 2026Noise-Aware Generalization: Robustness to In-Domain Noise and Out-of-Domain Generalization

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。