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 422 篇，第 3 / 9 页

101. NeurIPS 2025BAM-ICL: Causal Hijacking In-Context Learning with Budgeted Adversarial Manipulation
102. NeurIPS 2025Best-of-N Jailbreaking
103. NeurIPS 2025Better Language Model Inversion by Compactly Representing Next-Token Distributions
104. NeurIPS 2025Beyond $\tilde{O}(\sqrt{T})$ Constraint Violation for Online Convex Optimization with Adversarial Constraints
105. NeurIPS 2025Bits Leaked per Query: Information-Theoretic Bounds for Adversarial Attacks on LLMs
106. NeurIPS 2025Boosting Adversarial Transferability with Spatial Adversarial Alignment
107. NeurIPS 2025Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness
108. NeurIPS 2025Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations
109. NeurIPS 2025CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs
110. NeurIPS 2025Certifying Deep Network Risks and Individual Predictions with PAC-Bayes Loss via Localized Priors
111. NeurIPS 2025CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning
112. NeurIPS 2025Conformal Prediction under Lévy-Prokhorov Distribution Shifts: Robustness to Local and Global Perturbations
113. NeurIPS 2025Data Selection Matters: Towards Robust Instruction Tuning of Large Multimodal Models
114. NeurIPS 2025DenoiseRotator: Enhance Pruning Robustness for LLMs via Importance Concentration
115. NeurIPS 2025DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches
116. NeurIPS 2025DiffBreak: Is Diffusion-Based Purification Robust?
117. NeurIPS 2025Diffusion Guided Adversarial State Perturbations in Reinforcement Learning
118. NeurIPS 2025Distributional Adversarial Attacks and Training in Deep Hedging
119. NeurIPS 2025Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum
120. NeurIPS 2025Dynamic Siamese Expansion Framework for Improving Robustness in Online Continual Learning
121. NeurIPS 2025Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks
122. NeurIPS 2025E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis
123. NeurIPS 2025Enhancing CLIP Robustness via Cross-Modality Alignment
124. NeurIPS 2025Enhancing Graph Classification Robustness with Singular Pooling
125. NeurIPS 2025Enhancing Visual Prompting through Expanded Transformation Space and Overfitting Mitigation
126. NeurIPS 2025Evaluating and Learning Optimal Dynamic Treatment Regimes under Truncation by Death
127. NeurIPS 2025Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction
128. NeurIPS 2025Exploring the Noise Robustness of Online Conformal Prediction
129. NeurIPS 2025Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inference
130. NeurIPS 2025Fit the Distribution: Cross-Image/Prompt Adversarial Attacks on Multimodal Large Language Models
131. NeurIPS 2025Fortifying Time Series: DTW-Certified Robust Anomaly Detection
132. NeurIPS 2025FrameShield: Adversarially Robust Video Anomaly Detection
133. NeurIPS 2025Generative Data Augmentation via Diffusion Distillation, Adversarial Alignment, and Importance Reweighting
134. NeurIPS 2025Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability
135. NeurIPS 2025Heterogeneous Adversarial Play in Interactive Environments
136. NeurIPS 2025HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models
137. NeurIPS 2025IMPACT: Irregular Multi-Patch Adversarial Composition Based on Two‑Phase Optimization
138. NeurIPS 2025Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization
139. NeurIPS 2025Kernel von Mises Formula of the Influence Function
140. NeurIPS 2025Latent Space Factorization in LoRA
141. NeurIPS 2025Learning Robust Vision-Language Models from Natural Latent Spaces
142. NeurIPS 2025LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders
143. NeurIPS 2025MeCeFO: Enhancing LLM Training Robustness via Fault-Tolerant Optimization
144. NeurIPS 2025MIBP-Cert: Certified Training against Data Perturbations with Mixed-Integer Bilinear Programs
145. NeurIPS 2025MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents
146. NeurIPS 2025MixAT: Combining Continuous and Discrete Adversarial Training for LLMs
147. NeurIPS 2025Multi-Environment POMDPs: Discrete Model Uncertainty Under Partial Observability
148. NeurIPS 2025Multimodal Negative Learning
149. NeurIPS 2025No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!
150. NeurIPS 2025On the Optimality of the Median-of-Means Estimator under Adversarial Contamination

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。