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 60 篇，第 1 / 2 页

1. CVPR 20241-Lipschitz Layers Compared: Memory Speed and Certifiable Robustness
2. CVPR 2024A Bayesian Approach to OOD Robustness in Image Classification
3. CVPR 2024ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models
4. CVPR 2024Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Driving
5. CVPR 2024Adversarial Distillation Based on Slack Matching and Attribution Region Alignment
6. CVPR 2024Adversarial Score Distillation: When score distillation meets GAN
7. CVPR 2024ASAM: Boosting Segment Anything Model with Adversarial Tuning
8. CVPR 2024Attack To Defend: Exploiting Adversarial Attacks for Detecting Poisoned Models
9. CVPR 2024Boosting Adversarial Training via Fisher-Rao Norm-based Regularization
10. CVPR 2024Boosting Adversarial Transferability by Block Shuffle and Rotation
11. CVPR 2024CausalPC: Improving the Robustness of Point Cloud Classification by Causal Effect Identification
12. CVPR 2024DAP: A Dynamic Adversarial Patch for Evading Person Detectors
13. CVPR 2024Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization
14. CVPR 2024Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay
15. CVPR 2024DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection
16. CVPR 2024Dispel Darkness for Better Fusion: A Controllable Visual Enhancer based on Cross-modal Conditional Adversarial Learning
17. CVPR 2024Ensemble Diversity Facilitates Adversarial Transferability
18. CVPR 2024ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations
19. CVPR 2024Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training
20. CVPR 2024Friendly Sharpness-Aware Minimization
21. CVPR 2024Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds
22. CVPR 2024Improving Transferable Targeted Adversarial Attacks with Model Self-Enhancement
23. CVPR 2024Incorporating Geo-Diverse Knowledge into Prompting for Increased Geographical Robustness in Object Recognition
24. CVPR 2024Infrared Adversarial Car Stickers
25. CVPR 2024Initialization Matters for Adversarial Transfer Learning
26. CVPR 2024Label-Efficient Group Robustness via Out-of-Distribution Concept Curation
27. CVPR 2024Language-Driven Anchors for Zero-Shot Adversarial Robustness
28. CVPR 2024Learning to Transform Dynamically for Better Adversarial Transferability
29. CVPR 2024MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model
30. CVPR 2024MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models
31. CVPR 2024Model Inversion Robustness: Can Transfer Learning Help?
32. CVPR 2024NAPGuard: Towards Detecting Naturalistic Adversarial Patches
33. CVPR 2024On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation
34. CVPR 2024On the Robustness of Large Multimodal Models Against Image Adversarial Attacks
35. CVPR 2024One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models
36. CVPR 2024PAD: Patch-Agnostic Defense against Adversarial Patch Attacks
37. CVPR 2024PeerAiD: Improving Adversarial Distillation from a Specialized Peer Tutor
38. CVPR 2024Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving
39. CVPR 2024Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness
40. CVPR 2024Revisiting Adversarial Training at Scale
41. CVPR 2024Revisiting Adversarial Training Under Long-Tailed Distributions
42. CVPR 2024Robust Distillation via Untargeted and Targeted Intermediate Adversarial Samples
43. CVPR 2024Robust Image Denoising through Adversarial Frequency Mixup
44. CVPR 2024Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM
45. CVPR 2024RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
46. CVPR 2024Semantic-Aware Multi-Label Adversarial Attacks
47. CVPR 2024SlowFormer: Adversarial Attack on Compute and Energy Consumption of Efficient Vision Transformers
48. CVPR 2024Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement
49. CVPR 2024Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning
50. CVPR 2024Structure-Guided Adversarial Training of Diffusion Models

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。