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 311 篇，第 3 / 7 页

101. ICML 2025Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees
102. ICML 2025Adversarial Robustness via Deformable Convolution with Stochasticity
103. ICML 2025AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
104. ICML 2025All-Purpose Mean Estimation over R: Optimal Sub-Gaussianity with Outlier Robustness and Low Moments Performance
105. ICML 2025An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures
106. ICML 2025AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses
107. ICML 2025Average Certified Radius is a Poor Metric for Randomized Smoothing
108. ICML 2025Backdoor Attacks in Token Selection of Attention Mechanism
109. ICML 2025Bi-perspective Splitting Defense: Achieving Clean-Seed-Free Backdoor Security
110. ICML 2025Boosting Adversarial Robustness with CLAT: Criticality Leveraged Adversarial Training
111. ICML 2025Can DBNNs Robust to Environmental Noise for Resource-constrained Scenarios?
112. ICML 2025CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models
113. ICML 2025DiffAdvMAP: Flexible Diffusion-Based Framework for Generating Natural Unrestricted Adversarial Examples
114. ICML 2025Diffusion-based Adversarial Purification from the Perspective of the Frequency Domain
115. ICML 2025Diverse Prototypical Ensembles Improve Robustness to Subpopulation Shift
116. ICML 2025Efficient Robust Conformal Prediction via Lipschitz-Bounded Networks
117. ICML 2025Enhancing Adversarial Robustness with Conformal Prediction: A Framework for Guaranteed Model Reliability
118. ICML 2025Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss
119. ICML 2025Explaining the role of Intrinsic Dimensionality in Adversarial Training
120. ICML 2025Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards
121. ICML 2025Generalization and Robustness of the Tilted Empirical Risk
122. ICML 2025Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics
123. ICML 2025Identifying and Understanding Cross-Class Features in Adversarial Training
124. ICML 2025Improving Zero-Shot Adversarial Robustness in Vision-Language Models by Closed-form Alignment of Adversarial Path Simplices
125. ICML 2025Learning Adversarial MDPs with Stochastic Hard Constraints
126. ICML 2025Learning Gaussian DAG Models without Condition Number Bounds
127. ICML 2025Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals
128. ICML 2025LEVIS: Large Exact Verifiable Input Spaces for Neural Networks
129. ICML 2025Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization
130. ICML 2025MemFreezing: A Novel Adversarial Attack on Temporal Graph Neural Networks under Limited Future Knowledge
131. ICML 2025Multi-Armed Bandits with Interference: Bridging Causal Inference and Adversarial Bandits
132. ICML 2025Near-Optimal Consistency-Robustness Trade-Offs for Learning-Augmented Online Knapsack Problems
133. ICML 2025Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback
134. ICML 2025NeuronTune: Towards Self-Guided Spurious Bias Mitigation
135. ICML 2025Not All Wrong is Bad: Using Adversarial Examples for Unlearning
136. ICML 2025Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation
137. ICML 2025Omni-Angle Assault: An Invisible and Powerful Physical Adversarial Attack on Face Recognition
138. ICML 2025On the Adversarial Robustness of Multi-Kernel Clustering
139. ICML 2025On the Alignment between Fairness and Accuracy: from the Perspective of Adversarial Robustness
140. ICML 2025On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics
141. ICML 2025On the Diversity of Adversarial Ensemble Learning
142. ICML 2025On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training
143. ICML 2025On the Importance of Gaussianizing Representations
144. ICML 2025On the Learnability of Distribution Classes with Adaptive Adversaries
145. ICML 2025On the Local Complexity of Linear Regions in Deep ReLU Networks
146. ICML 2025On the Tension between Byzantine Robustness and No-Attack Accuracy in Distributed Learning
147. ICML 2025One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy
148. ICML 2025Optimal Fair Learning Robust to Adversarial Distribution Shift
149. ICML 2025Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach
150. ICML 2025Phase and Amplitude-aware Prompting for Enhancing Adversarial Robustness

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。