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 334 篇，第 3 / 7 页

101. ICLR 2024Label-Noise Robust Diffusion Models
102. ICLR 2024Large Language Models Are Not Robust Multiple Choice Selectors
103. ICLR 2024Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds
104. ICLR 2024LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
105. ICLR 2024Mitigating Emergent Robustness Degradation while Scaling Graph Learning
106. ICLR 2024Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing
107. ICLR 2024On Adversarial Training without Perturbing all Examples
108. ICLR 2024On the Vulnerability of Adversarially Trained Models Against Two-faced Attacks
109. ICLR 2024Optimal transport based adversarial patch to leverage large scale attack transferability
110. ICLR 2024Out-Of-Domain Unlabeled Data Improves Generalization
111. ICLR 2024Provably Robust Conformal Prediction with Improved Efficiency
112. ICLR 2024PubDef: Defending Against Transfer Attacks From Public Models
113. ICLR 2024Pushing Boundaries: Mixup's Influence on Neural Collapse
114. ICLR 2024Quantifying and Enhancing Multi-modal Robustness with Modality Preference
115. ICLR 2024Rethinking Model Ensemble in Transfer-based Adversarial Attacks
116. ICLR 2024Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula
117. ICLR 2024Robust Classification via Regression for Learning with Noisy Labels
118. ICLR 2024Robust NAS under adversarial training: benchmark, theory, and beyond
119. ICLR 2024Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
120. ICLR 2024SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer
121. ICLR 2024Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
122. ICLR 2024The Effectiveness of Random Forgetting for Robust Generalization
123. ICLR 2024Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach
124. ICLR 2024Theoretical Understanding of Learning from Adversarial Perturbations
125. ICLR 2024Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback
126. ICLR 2024Towards Robust Out-of-Distribution Generalization Bounds via Sharpness
127. ICLR 2024Understanding Certified Training with Interval Bound Propagation
128. ICLR 2024Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift
129. ICLR 2024Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks
130. ICLR 2024Why is SAM Robust to Label Noise?
131. ICML 2024$\texttt{MoE-RBench}$: Towards Building Reliable Language Models with Sparse Mixture-of-Experts
132. ICML 2024Adversarial Attacks on Combinatorial Multi-Armed Bandits
133. ICML 2024Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies
134. ICML 2024Ai-sampler: Adversarial Learning of Markov kernels with involutive maps
135. ICML 2024Attack-free Evaluating and Enhancing Adversarial Robustness on Categorical Data
136. ICML 2024BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
137. ICML 2024Be Your Own Neighborhood: Detecting Adversarial Examples by the Neighborhood Relations Built on Self-Supervised Learning
138. ICML 2024Benign Overfitting in Adversarial Training of Neural Networks
139. ICML 2024Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents
140. ICML 2024Bridging Data Gaps in Diffusion Models with Adversarial Noise-Based Transfer Learning
141. ICML 2024Can Implicit Bias Imply Adversarial Robustness?
142. ICML 2024Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations
143. ICML 2024Contamination-Resilient Anomaly Detection via Adversarial Learning on Partially-Observed Normal and Anomalous Data
144. ICML 2024Controllable Prompt Tuning For Balancing Group Distributional Robustness
145. ICML 2024CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks
146. ICML 2024DataFreeShield: Defending Adversarial Attacks without Training Data
147. ICML 2024Deep Networks Always Grok and Here is Why
148. ICML 2024Density Ratio Estimation with Doubly Strong Robustness
149. ICML 2024Diffusion Models Demand Contrastive Guidance for Adversarial Purification to Advance
150. ICML 2024Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing

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。