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 110 篇，第 2 / 3 页

51. NeurIPS 2025FrameShield: Adversarially Robust Video Anomaly Detection
52. NeurIPS 2025Generative Data Augmentation via Diffusion Distillation, Adversarial Alignment, and Importance Reweighting
53. NeurIPS 2025Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability
54. NeurIPS 2025Heterogeneous Adversarial Play in Interactive Environments
55. NeurIPS 2025HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models
56. NeurIPS 2025IMPACT: Irregular Multi-Patch Adversarial Composition Based on Two‑Phase Optimization
57. NeurIPS 2025Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization
58. NeurIPS 2025Kernel von Mises Formula of the Influence Function
59. NeurIPS 2025Latent Space Factorization in LoRA
60. NeurIPS 2025Learning Robust Vision-Language Models from Natural Latent Spaces
61. NeurIPS 2025LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders
62. NeurIPS 2025MeCeFO: Enhancing LLM Training Robustness via Fault-Tolerant Optimization
63. NeurIPS 2025MIBP-Cert: Certified Training against Data Perturbations with Mixed-Integer Bilinear Programs
64. NeurIPS 2025MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents
65. NeurIPS 2025MixAT: Combining Continuous and Discrete Adversarial Training for LLMs
66. NeurIPS 2025Multi-Environment POMDPs: Discrete Model Uncertainty Under Partial Observability
67. NeurIPS 2025Multimodal Negative Learning
68. NeurIPS 2025No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!
69. NeurIPS 2025On the Optimality of the Median-of-Means Estimator under Adversarial Contamination
70. NeurIPS 2025On the Robustness of Transformers against Context Hijacking for Linear Classification
71. NeurIPS 2025On the Robustness of Verbal Confidence of LLMs in Adversarial Attacks
72. NeurIPS 2025Optimal Control for Transformer Architectures: Enhancing Generalization, Robustness and Efficiency
73. NeurIPS 2025OSTAR: Optimized Statistical Text-classifier with Adversarial Resistance
74. NeurIPS 2025Parameter-free Algorithms for the Stochastically Extended Adversarial Model
75. NeurIPS 2025PCA++: How Uniformity Induces Robustness to Background Noise in Contrastive Learning
76. NeurIPS 2025Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback
77. NeurIPS 2025ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search
78. NeurIPS 2025Remarkable Robustness of LLMs: Stages of Inference?
79. NeurIPS 2025Reverse Engineering Human Preferences with Reinforcement Learning
80. NeurIPS 2025Robust Equilibria in Continuous Games: From Strategic to Dynamic Robustness
81. NeurIPS 2025Robust learning of halfspaces under log-concave marginals
82. NeurIPS 2025Robust Satisficing Gaussian Process Bandits Under Adversarial Attacks
83. NeurIPS 2025Robust SuperAlignment: Weak-to-Strong Robustness Generalization for Vision-Language Models
84. NeurIPS 2025Robustifying Learning-Augmented Caching Efficiently without Compromising 1-Consistency
85. NeurIPS 2025Robustness in Both Domains: CLIP Needs a Robust Text Encoder
86. NeurIPS 2025Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning
87. NeurIPS 2025Scalable Neural Network Geometric Robustness Validation via Hölder Optimisation
88. NeurIPS 2025Scaling Data-Driven Probabilistic Robustness Analysis for Semantic Segmentation Neural Networks
89. NeurIPS 2025SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations
90. NeurIPS 2025Self-Refining Language Model Anonymizers via Adversarial Distillation
91. NeurIPS 2025Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence
92. NeurIPS 2025Statistical Analysis of an Adversarial Bayesian Weak Supervision Method
93. NeurIPS 2025Stochastic Shortest Path with Sparse Adversarial Costs
94. NeurIPS 2025Taming Adversarial Constraints in CMDPs
95. NeurIPS 2025The Cost of Compression: Tight Quadratic Black-Box Attacks on Sketches for $\ell_2$ Norm Estimation
96. NeurIPS 2025The Cost of Robustness: Tighter Bounds on Parameter Complexity for Robust Memorization in ReLU Nets
97. NeurIPS 2025The Fluorescent Veil: A Stealthy and Effective Physical Adversarial Patch Against Traffic Sign Recognition
98. NeurIPS 2025The Good, the Bad and the Ugly: Meta-Analysis of Watermarks, Transferable Attacks and Adversarial Defenses
99. NeurIPS 2025The Impact of Coreset Selection on Spurious Correlations and Group Robustness
100. NeurIPS 2025The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels

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。