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 331 篇，第 3 / 7 页

101. ICLR 2025Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI
102. ICLR 2025Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step
103. ICLR 2025Adversarial Search Engine Optimization for Large Language Models
104. ICLR 2025Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data
105. ICLR 2025Adversarial Training for Defense Against Label Poisoning Attacks
106. ICLR 2025Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized Embeddings
107. ICLR 2025Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness
108. ICLR 2025AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption
109. ICLR 2025AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
110. ICLR 2025Algorithmic Stability Based Generalization Bounds for Adversarial Training
111. ICLR 2025Aligned LLMs Are Not Aligned Browser Agents
112. ICLR 2025Artificial Kuramoto Oscillatory Neurons
113. ICLR 2025ASTrA: Adversarial Self-supervised Training with Adaptive-Attacks
114. ICLR 2025Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness
115. ICLR 2025Boosting the visual interpretability of CLIP via adversarial fine-tuning
116. ICLR 2025Certified Robustness Under Bounded Levenshtein Distance
117. ICLR 2025CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification
118. ICLR 2025Confidence Elicitation: A New Attack Vector for Large Language Models
119. ICLR 2025Deep MMD Gradient Flow without adversarial training
120. ICLR 2025Democratic Training Against Universal Adversarial Perturbations
121. ICLR 2025Diffusion State-Guided Projected Gradient for Inverse Problems
122. ICLR 2025Dissecting Adversarial Robustness of Multimodal LM Agents
123. ICLR 2025Does Refusal Training in LLMs Generalize to the Past Tense?
124. ICLR 2025DRoP: Distributionally Robust Data Pruning
125. ICLR 2025Endless Jailbreaks with Bijection Learning
126. ICLR 2025Endowing Visual Reprogramming with Adversarial Robustness
127. ICLR 2025Enhancing Prediction Performance through Influence Measure
128. ICLR 2025Enhancing Robust Fairness via Confusional Spectral Regularization
129. ICLR 2025Estimating the Probabilities of Rare Outputs in Language Models
130. ICLR 2025Exact Certification of (Graph) Neural Networks Against Label Poisoning
131. ICLR 2025Exploring The Forgetting in Adversarial Training: A Novel Method for Enhancing Robustness
132. ICLR 2025Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
133. ICLR 2025Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks
134. ICLR 2025GOttack: Universal Adversarial Attacks on Graph Neural Networks via Graph Orbits Learning
135. ICLR 2025GPromptShield: Elevating Resilience in Graph Prompt Tuning Against Adversarial Attacks
136. ICLR 2025GSBA$^K$: $top$-$K$ Geometric Score-based Black-box Attack
137. ICLR 2025Improved Diffusion-based Generative Model with Better Adversarial Robustness
138. ICLR 2025Improving Generalization and Robustness in SNNs Through Signed Rate Encoding and Sparse Encoding Attacks
139. ICLR 2025Indirect Gradient Matching for Adversarial Robust Distillation
140. ICLR 2025Input Space Mode Connectivity in Deep Neural Networks
141. ICLR 2025Is Your Multimodal Language Model Oversensitive to Safe Queries?
142. ICLR 2025Jailbreaking as a Reward Misspecification Problem
143. ICLR 2025Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
144. ICLR 2025Learning Randomized Algorithms with Transformers
145. ICLR 2025Long-tailed Adversarial Training with Self-Distillation
146. ICLR 2025Measuring Non-Adversarial Reproduction of Training Data in Large Language Models
147. ICLR 2025Minimax Optimal Two-Stage Algorithm For Moment Estimation Under Covariate Shift
148. ICLR 2025MixMax: Distributional Robustness in Function Space via Optimal Data Mixtures
149. ICLR 2025Model-Free Offline Reinforcement Learning with Enhanced Robustness
150. ICLR 2025Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning

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。