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 2 / 9 页

51. NeurIPS 2026Near-Optimal Regret in Adversarial Kernel Bandits
52. NeurIPS 2026Near-Optimal Stochastic Linear Bandits with Delay
53. NeurIPS 2026Nearly-Optimal Algorithm for Adversarial Kernelized Bandits
54. NeurIPS 2026On Lipschitz Explosion in Deep Neural Networks with Normalization: Consequences for Optimization and Robustness
55. NeurIPS 2026Optimal In-context Adaptivity and Distributional Robustness of Transformers
56. NeurIPS 2026Pan-FM: A Pan-Organ Foundation Model with Saliency-Guided Masking for Missing Robustness
57. NeurIPS 2026Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injection
58. NeurIPS 2026Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays
59. NeurIPS 2026Reliable Abstention under Adversarial Injections: Lower Bounds and New Upper Bounds
60. NeurIPS 2026Residual Calibration via Local Feature-Space Refinement
61. NeurIPS 2026Revisiting On-policy Adversarial Black-Box Distillation: Calibrating Groupwise Reward Geometry for Effective Advantage Construction
62. NeurIPS 2026Robust and Scalable Collaborative Learning via Pull-Based Epidemic Communication
63. NeurIPS 2026Robust Satisficing Ensemble: Scalable Model Aggregation Under Distribution Shifts
64. NeurIPS 2026SAFE-FEC: Semantically Constrained Adversarial Frontier Evolution for Factual Error Correction
65. NeurIPS 2026Should We Pay This Much for Robustness? Efficient Proxy Certificates with Marginal Guarantees
66. NeurIPS 2026Stable Alpha: Adversarial Invariant Representation Learning for Nonlinear Asset Pricing under Temporal Distribution Shifts
67. NeurIPS 2026Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling
68. NeurIPS 2026Surrogate Calibration for Transferable Adversarial Attacks against Black-Box MLLMs
69. NeurIPS 2026SynDORBench: Evaluating LVLM Perceptual Robustness Under Physically Constrained Visibility Conditions
70. NeurIPS 2026Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data
71. NeurIPS 2026Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles
72. NeurIPS 2026The Adversarial Gait: Detecting Visual Adversarial Attacks against Vision-Language Models via Self-Targeted Gradient Characterization
73. NeurIPS 2026The Web Doesn't Sit Still: Adversarial Self-Evolving Attacks on Search Agents
74. NeurIPS 2026Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models
75. NeurIPS 2026Universal Cross-Prompt Adversarial Attacks on Promptable Concept Segmentation
76. NeurIPS 2026Variational Cover Modification Steganography
77. NeurIPS 2026When and Why Adversarial Training Improves PINNs: A Neural Tangent Kernel Perspective
78. NeurIPS 2026When Are Semivalue-Based Decisions Identifiable? Robust Data Selection under Utility Ambiguity
79. NeurIPS 2026When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?
80. NeurIPS 2026When to Inject the Target: Stage-Decoupled Guidance for Diffusion-Based Targeted Adversarial Attacks
81. NeurIPS 2026When Uncertainty Is the Target: Adversarial Attacks on Uncertainty-Aware Predictors
82. NeurIPS 2025A data and task-constrained mechanistic model of the mouse outer retina shows robustness to contrast variations
83. NeurIPS 2025A Near-optimal, Scalable and Parallelizable Framework for Stochastic Bandits Robust to Adversarial Corruptions and Beyond
84. NeurIPS 2025A Unified Approach to Submodular Maximization Under Noise
85. NeurIPS 2025Accelerated Vertical Federated Adversarial Learning through Decoupling Layer-Wise Dependencies
86. NeurIPS 2025AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness
87. NeurIPS 2025Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
88. NeurIPS 2025Adv-SSL: Adversarial Self-Supervised Representation Learning with Theoretical Guarantees
89. NeurIPS 2025Adversarial Diffusion for Robust Reinforcement Learning
90. NeurIPS 2025Adversarial generalization of unfolding (model-based) networks
91. NeurIPS 2025Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text
92. NeurIPS 2025Adversarial Robustness of Nonparametric Regression
93. NeurIPS 2025Adversary Aware Optimization for Robust Defense
94. NeurIPS 2025AdvPrefix: An Objective for Nuanced LLM Jailbreaks
95. NeurIPS 2025Alias-Free ViT: Fractional Shift Invariance via Linear Attention
96. NeurIPS 2025An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction
97. NeurIPS 2025AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant Adversarial Patches
98. NeurIPS 2025Attention! Your Vision Language Model Could Be Maliciously Manipulated
99. NeurIPS 2025AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration
100. NeurIPS 2025Backdoor Mitigation via Invertible Pruning Masks

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。