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 327 篇，第 3 / 7 页

101. ICLR 2025Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching
102. ICLR 2025On Minimizing Adversarial Counterfactual Error in Adversarial Reinforcement Learning
103. ICLR 2025Optimizing importance weighting in the presence of sub-population shifts
104. ICLR 2025PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs
105. ICLR 2025Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization
106. ICLR 2025Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning
107. ICLR 2025Provably Safeguarding a Classifier from OOD and Adversarial Samples
108. ICLR 2025Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off
109. ICLR 2025Robust Feature Learning for Multi-Index Models in High Dimensions
110. ICLR 2025Robust LLM safeguarding via refusal feature adversarial training
111. ICLR 2025Robust Representation Consistency Model via Contrastive Denoising
112. ICLR 2025Robust Transfer of Safety-Constrained Reinforcement Learning Agents
113. ICLR 2025Robustness Auditing for Linear Regression: To Singularity and Beyond
114. ICLR 2025Robustness Inspired Graph Backdoor Defense
115. ICLR 2025Robustness Reprogramming for Representation Learning
116. ICLR 2025Selective Unlearning via Representation Erasure Using Domain Adversarial Training
117. ICLR 2025Shh, don't say that! Domain Certification in LLMs
118. ICLR 2025Speech Robust Bench: A Robustness Benchmark For Speech Recognition
119. ICLR 2025Stochastic Bandits Robust to Adversarial Attacks
120. ICLR 2025Strong Preferences Affect the Robustness of Preference Models and Value Alignment
121. ICLR 2025Tailoring Mixup to Data for Calibration
122. ICLR 2025Targeted Attack Improves Protection against Unauthorized Diffusion Customization
123. ICLR 2025TASAR: Transfer-based Attack on Skeletal Action Recognition
124. ICLR 2025Tight Clusters Make Specialized Experts
125. ICLR 2025To Tackle Adversarial Transferability: A Novel Ensemble Training Method with Fourier Transformation
126. ICLR 2025Towards Certification of Uncertainty Calibration under Adversarial Attacks
127. ICLR 2025Towards Scalable Topological Regularizers
128. ICLR 2025Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
129. ICLR 2025Training Robust Ensembles Requires Rethinking Lipschitz Continuity
130. ICLR 2025Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
131. ICLR 2025Verifying Properties of Binary Neural Networks Using Sparse Polynomial Optimization
132. ICLR 2025Zero-cost Proxy for Adversarial Robustness Evaluation
133. ICML 2025Adapting to Evolving Adversaries with Regularized Continual Robust Training
134. ICML 2025Adaptive Median Smoothing: Adversarial Defense for Unlearned Text-to-Image Diffusion Models at Inference Time
135. ICML 2025Adversarial Combinatorial Semi-bandits with Graph Feedback
136. ICML 2025Adversarial Inputs for Linear Algebra Backends
137. ICML 2025Adversarial Perturbations Are Formed by Iteratively Learning Linear Combinations of the Right Singular Vectors of the Adversarial Jacobian
138. ICML 2025Adversarial Reasoning at Jailbreaking Time
139. ICML 2025Adversarial Robust Generalization of Graph Neural Networks
140. ICML 2025Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees
141. ICML 2025Adversarial Robustness via Deformable Convolution with Stochasticity
142. ICML 2025AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
143. ICML 2025All-Purpose Mean Estimation over R: Optimal Sub-Gaussianity with Outlier Robustness and Low Moments Performance
144. ICML 2025An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures
145. ICML 2025AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses
146. ICML 2025Average Certified Radius is a Poor Metric for Randomized Smoothing
147. ICML 2025Backdoor Attacks in Token Selection of Attention Mechanism
148. ICML 2025Bi-perspective Splitting Defense: Achieving Clean-Seed-Free Backdoor Security
149. ICML 2025Boosting Adversarial Robustness with CLAT: Criticality Leveraged Adversarial Training
150. ICML 2025Can DBNNs Robust to Environmental Noise for Resource-constrained Scenarios?

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。