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 1,290 篇，第 3 / 26 页

101. ICLR 2026Obfuscated Activations Bypass LLM Latent-Space Defenses
102. ICLR 2026On Discovering Algorithms for Adversarial Imitation Learning
103. ICLR 2026On the Bayes Inconsistency of Disagreement Discrepancy Surrogates
104. ICLR 2026On the Impact of the Utility in Semivalue-based Data Valuation
105. ICLR 2026On the Interaction of Compressibility and Adversarial Robustness
106. ICLR 2026ON THE ROLE OF IMPLICIT REGULARIZATION OF STOCHASTIC GRADIENT DESCENT IN GROUP ROBUSTNESS
107. ICLR 2026On the Tension Between Optimality and Adversarial Robustness in Policy Optimization
108. ICLR 2026Online Conformal Prediction with Adversarial Feedback via Regret Minimization
109. ICLR 2026Pay Less Attention to Function Words for Free Robustness of Vision-Language Models
110. ICLR 2026QUEST: A robust attention formulation using query-modulated spherical attention
111. ICLR 2026RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
112. ICLR 2026Reducing information dependency does not cause training data privacy. Adversarially non-robust features do.
113. ICLR 2026Robust Adversarial Attacks Against Unknown Disturbance via Inverse Gradient Sample
114. ICLR 2026Robust Adversarial Quantification via Conflict-Aware Evidential Deep Learning
115. ICLR 2026Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation
116. ICLR 2026Robust Federated Inference
117. ICLR 2026Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling
118. ICLR 2026Robust LLM Unlearning via Post Judgment and Multi-round Thinking
119. ICLR 2026Robust Spiking Neural Networks Against Adversarial Attacks
120. ICLR 2026Robustness in Text-Attributed Graph Learning: Insights, Trade-offs, and New Defenses
121. ICLR 2026Robustness of Probabilistic Models to Low-Quality Data: A Multi-Perspective Analysis
122. ICLR 2026Sampling-aware Adversarial Attacks Against Large Language Models
123. ICLR 2026Set Representation Auxiliary Learning with Adversarial Encoding Perturbation and Optimization
124. ICLR 2026Stretching Beyond the Obvious: A Gradient-Free Framework to Unveil the Hidden Landscape of Visual Invariance
125. ICLR 2026Testing Most Influential Sets
126. ICLR 2026The Price of Robustness: Stable Classifiers Need Overparameterization
127. ICLR 2026The Shape of Adversarial Influence: Characterizing LLM Latent Spaces with Persistent Homology
128. ICLR 2026Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks
129. ICLR 2026Time-To-Inconsistency: A Survival Analysis of Large Language Model Robustness to Adversarial Attacks
130. ICLR 2026Training Dynamics Impact Post-Training Quantization Robustness
131. ICLR 2026Transferable and Stealthy Adversarial Attacks on Large Vision-Language Models
132. ICLR 2026TriQDef: Disrupting Semantic and Gradient Alignment to Prevent Adversarial Patch Transferability in Quantized Neural Networks
133. ICLR 2026Tug-of-War No More: Harmonizing Accuracy and Robustness in Vision-Language Models via Stability-Aware Task Vector Merging
134. ICLR 2026Understanding and Improving Continuous LLM Adversarial Training via In-context Learning Theory
135. ICLR 2026Understanding Sensitivity of Differential Attention through the Lens of Adversarial Robustness
136. ICLR 2026Untraceable DeepFakes via Traceable Fingerprint Elimination
137. ICLR 2026VEAttack: Downstream-agnostic Vision Encoder Attack against Large Vision Language Models
138. ICLR 2026Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning
139. ICLR 2026When Flatness Does (Not) Guarantee Adversarial Robustness
140. ICLR 2026Why Adversarially Train Diffusion Models?
141. ICLR 2026Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information
142. ICLR 2026Zero-Sacrifice Persistent-Robustness Adversarial Defense for Pre-Trained Encoders
143. ICML 2026``Someone Hid It!'': Query-Agnostic Black-Box Attacks on LLM-Based Retrieval
144. ICML 2026A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness
145. ICML 2026Adaptive Probe-based Steering for Robust LLM Jailbreaking
146. ICML 2026Adaptively Robust Resettable Streaming
147. ICML 2026Adversarial Attacks and Robust Training for Hypergraph Neural Networks
148. ICML 2026Adversarial Robustness of Implicit Neural Representation-Based Classifiers
149. ICML 2026Adversarial Vulnerability from Interference Between Features in Superposition
150. ICML 2026AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing

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。