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 4 / 7 页

151. ICML 2025Pixel-level Certified Explanations via Randomized Smoothing
152. ICML 2025Pixel2Feature Attack (P2FA): Rethinking the Perturbed Space to Enhance Adversarial Transferability
153. ICML 2025Position: Certified Robustness Does Not (Yet) Imply Model Security
154. ICML 2025Probably Approximately Global Robustness Certification
155. ICML 2025Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing
156. ICML 2025Quadratic Upper Bound for Boosting Robustness
157. ICML 2025REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective
158. ICML 2025Robust Automatic Modulation Classification with Fuzzy Regularization
159. ICML 2025RobustLight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal Control
160. ICML 2025RobustZero: Enhancing MuZero Reinforcement Learning Robustness to State Perturbations
161. ICML 2025ROME is Forged in Adversity: Robust Distilled Datasets via Information Bottleneck
162. ICML 2025Sample-specific Noise Injection for Diffusion-based Adversarial Purification
163. ICML 2025Scaling Trends in Language Model Robustness
164. ICML 2025Self-Consuming Generative Models with Adversarially Curated Data
165. ICML 2025Self-supervised Adversarial Purification for Graph Neural Networks
166. ICML 2025SGD Jittering: A Training Strategy for Robust and Accurate Model-Based Architectures
167. ICML 2025Splitting & Integrating: Out-of-Distribution Detection via Adversarial Gradient Attribution
168. ICML 2025Statistical Hypothesis Testing for Auditing Robustness in Language Models
169. ICML 2025Towards Robust Influence Functions with Flat Validation Minima
170. ICML 2025Towards Robustness and Explainability of Automatic Algorithm Selection
171. ICML 2025TtBA: Two-third Bridge Approach for Decision-Based Adversarial Attack
172. ICML 2025Understanding Model Ensemble in Transferable Adversarial Attack
173. ICML 2025Unified Breakdown Analysis for Byzantine Robust Gossip
174. ICML 2025Universal Neural Optimal Transport
175. ICML 2025Unveiling AI's Blind Spots: An Oracle for In-Domain, Out-of-Domain, and Adversarial Errors
176. ICML 2025Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning
177. ICML 2025When and How Does CLIP Enable Domain and Compositional Generalization?
178. ICML 2025X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
179. ICML 2024$\texttt{MoE-RBench}$: Towards Building Reliable Language Models with Sparse Mixture-of-Experts
180. ICML 2024Adversarial Attacks on Combinatorial Multi-Armed Bandits
181. ICML 2024Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies
182. ICML 2024Ai-sampler: Adversarial Learning of Markov kernels with involutive maps
183. ICML 2024Attack-free Evaluating and Enhancing Adversarial Robustness on Categorical Data
184. ICML 2024BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
185. ICML 2024Be Your Own Neighborhood: Detecting Adversarial Examples by the Neighborhood Relations Built on Self-Supervised Learning
186. ICML 2024Benign Overfitting in Adversarial Training of Neural Networks
187. ICML 2024Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents
188. ICML 2024Bridging Data Gaps in Diffusion Models with Adversarial Noise-Based Transfer Learning
189. ICML 2024Can Implicit Bias Imply Adversarial Robustness?
190. ICML 2024Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations
191. ICML 2024Contamination-Resilient Anomaly Detection via Adversarial Learning on Partially-Observed Normal and Anomalous Data
192. ICML 2024Controllable Prompt Tuning For Balancing Group Distributional Robustness
193. ICML 2024CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks
194. ICML 2024DataFreeShield: Defending Adversarial Attacks without Training Data
195. ICML 2024Deep Networks Always Grok and Here is Why
196. ICML 2024Density Ratio Estimation with Doubly Strong Robustness
197. ICML 2024Diffusion Models Demand Contrastive Guidance for Adversarial Purification to Advance
198. ICML 2024Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing
199. ICML 2024Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior
200. ICML 2024Enhancing Adversarial Robustness in SNNs with Sparse Gradients

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。