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 79 篇，第 1 / 2 页

1. ICLR 2023(Certified!!) Adversarial Robustness for Free!
2. ICLR 2023A law of adversarial risk, interpolation, and label noise
3. ICLR 2023A Unified Algebraic Perspective on Lipschitz Neural Networks
4. ICLR 2023Adversarial Attacks on Adversarial Bandits
5. ICLR 2023Adversarial Imitation Learning with Preferences
6. ICLR 2023Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks
7. ICLR 2023AGRO: Adversarial discovery of error-prone Groups for Robust Optimization
8. ICLR 2023Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness
9. ICLR 2023Arbitrary Virtual Try-on Network: Characteristics Representation and Trade-off between Body and Clothing
10. ICLR 2023Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts
11. ICLR 2023Boosting Adversarial Transferability using Dynamic Cues
12. ICLR 2023Brain-like representational straightening of natural movies in robust feedforward neural networks
13. ICLR 2023Can CNNs Be More Robust Than Transformers?
14. ICLR 2023Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries
15. ICLR 2023Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation
16. ICLR 2023Certified Training: Small Boxes are All You Need
17. ICLR 2023Chasing All-Round Graph Representation Robustness: Model, Training, and Optimization
18. ICLR 2023Data augmentation alone can improve adversarial training
19. ICLR 2023DAVA: Disentangling Adversarial Variational Autoencoder
20. ICLR 2023Defending against Adversarial Audio via Diffusion Model
21. ICLR 2023DensePure: Understanding Diffusion Models for Adversarial Robustness
22. ICLR 2023Distributionally Robust Post-hoc Classifiers under Prior Shifts
23. ICLR 2023Diversify and Disambiguate: Out-of-Distribution Robustness via Disagreement
24. ICLR 2023Domain Generalisation via Domain Adaptation: An Adversarial Fourier Amplitude Approach
25. ICLR 2023Efficient Certified Training and Robustness Verification of Neural ODEs
26. ICLR 2023Empowering Graph Representation Learning with Test-Time Graph Transformation
27. ICLR 2023Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness
28. ICLR 2023Exploring perceptual straightness in learned visual representations
29. ICLR 2023Extracting Robust Models with Uncertain Examples
30. ICLR 2023Finding Actual Descent Directions for Adversarial Training
31. ICLR 2023Finding the Global Semantic Representation in GAN through Fréchet Mean
32. ICLR 2023Fooling SHAP with Stealthily Biased Sampling
33. ICLR 2023Free Lunch for Domain Adversarial Training: Environment Label Smoothing
34. ICLR 2023Holistic Adversarially Robust Pruning
35. ICLR 2023ILA-DA: Improving Transferability of Intermediate Level Attack with Data Augmentation
36. ICLR 2023Inequality phenomenon in $l_{\infty}$-adversarial training, and its unrealized threats
37. ICLR 2023Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?
38. ICLR 2023Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations
39. ICLR 2023Learning MLPs on Graphs: A Unified View of Effectiveness, Robustness, and Efficiency
40. ICLR 2023Localized Randomized Smoothing for Collective Robustness Certification
41. ICLR 2023Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples
42. ICLR 2023Malign Overfitting: Interpolation and Invariance are Fundamentally at Odds
43. ICLR 2023Mind the Pool: Convolutional Neural Networks Can Overfit Input Size
44. ICLR 2023Near-Optimal Adversarial Reinforcement Learning with Switching Costs
45. ICLR 2023Near-optimal Coresets for Robust Clustering
46. ICLR 2023Neural Architecture Design and Robustness: A Dataset
47. ICLR 2023On Achieving Optimal Adversarial Test Error
48. ICLR 2023On Explaining Neural Network Robustness with Activation Path
49. ICLR 2023On the Perils of Cascading Robust Classifiers
50. ICLR 2023On the Robustness of Safe Reinforcement Learning under Observational Perturbations

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。