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 1 / 26 页

1. CVPR 2026A Combination of Noise and Bilateral Filters Achieve Supralinear and
2. CVPR 2026A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large
3. CVPR 2026A Unified Perspective on Adversarial Membership Manipulation in Vision Models
4. CVPR 2026AdvFM Lookahead Flow-Matching Velocity-Field Attacks for Imperceptible and Transferable Adversarial
5. CVPR 2026AGFT Alignment-Guided Fine-Tuning for Zero-Shot Adversarial Robustness of Vision-Language Models
6. CVPR 2026All Vehicles Can Lie Efficient Adversarial Defense in Fully Untrusted-Vehicle
7. CVPR 2026AntiStyler Defending Object Detection Models Against Adversarial Patch Attacks Using
8. CVPR 2026Attack for Defense Adversarial Agents for Point Prompt Optimization Empowering
9. CVPR 2026CamPI Physical Adversarial Examples through Camera Power Signal Injection
10. CVPR 2026ChartR Evaluating Reasoning Accuracy and Robustness in Chart Question Answering
11. CVPR 2026Consistency Beyond Contrast Enhancing Open-Vocabulary Object Detection Robustness via Contextual
12. CVPR 2026Detecting Compressed AI-Generated Images via Phase Spectrum Robustness
13. CVPR 2026Diffusion-Based Native Adversarial Synthesis for Enhanced Medical Segmentation Generalization
14. CVPR 2026DPL Decoupled Prototype Learning for Enhancing Robustness of Vision-Language Transformers
15. CVPR 2026Echoes of Ownership Adversarial-Guided Dual Injection for Copyright Protection in
16. CVPR 2026FedAFD Multimodal Federated Learning via Adversarial Fusion and Distillation
17. CVPR 2026FedCART Tackling Long-Tailed Distributions in Federated Adversarial Training via Classifier
18. CVPR 2026Fractal Camouflage A Bio-Inspired Approach for Multi-Scale Adversarial Attacks in
19. CVPR 2026Generative Adversarial Perturbations with Cross-paradigm Transferability on Localized Crowd Counting
20. CVPR 2026Good Can Sometimes be Bad A Unified Attack against 3D
21. CVPR 2026Improving Adversarial Transferability with Local Perturbation Augmentation
22. CVPR 2026IrisFP Adversarial-Example-based Model Fingerprinting with Enhanced Uniqueness and Robustness
23. CVPR 2026Learning Mutual View Information Graph for Adaptive Adversarial Collaborative Perception
24. CVPR 2026Mitigating Error Amplification in Fast Adversarial Training
25. CVPR 2026Multi-Paradigm Collaborative Adversarial Attack Against Multi-Modal Large Language Models
26. CVPR 2026Omni-Attack Adversarial Attacks on Open-Ended VQA in Black-Box Multimodal LLMs
27. CVPR 2026On the Role of Temporal Granularity in the Robustness of
28. CVPR 2026Out of Sight Out of Track Adversarial Attacks on Propagation-based
29. CVPR 2026Perception Characteristics Distance Measuring Stability and Robustness of Perception System
30. CVPR 2026Physical Adversarial Clothing Evades Visible-Thermal Detectors via Non-Overlapping RGB-T Pattern
31. CVPR 2026RevINN An End-to-End Invertible Neural Network for Reversible Adversarial Examples
32. CVPR 2026Robustness Under Data Scarcity Few-Shot Continual Adversarial Training for Evolving
33. CVPR 2026SABER Spatially Consistent 3D Universal Adversarial Objects for BEV Detectors
34. CVPR 2026SafeLogo Turning Your Logos into Jailbreak Shields via Micro-Regional Adversarial
35. CVPR 2026Shedding Light on VLN Robustness A Black-box Framework for Indoor
36. CVPR 2026Spectral Super-Resolution via Adversarial Unfolding and Data-Driven Spectrum Regularization From
37. CVPR 2026Taming the Long Tail Rebalancing Adversarial Training via Adaptive Perturbation
38. CVPR 2026The Geometry of Robustness Optimizing Loss Landscape Curvature and Feature
39. CVPR 2026The Image as Its Own Reward Reinforcement Learning with Adversarial
40. CVPR 2026Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems
41. CVPR 2026Towards Reliable Evaluation of Adversarial Robustness for Spiking Neural Networks
42. CVPR 2026Transform to Transfer Boosting Adversarial Attack Transferability on Vision-Language Pre-training
43. CVPR 2026TTP Test-Time Padding for Adversarial Detection and Robust Adaptation on
44. CVPR 2026UniGame Turning a Unified Multimodal Model Into Its Own Adversary
45. CVPR 2026V-Attack Targeting Disentangled Value Features for Controllable Adversarial Attacks on
46. CVPR 2026Verifying Neural Network Robustness with Dual Perturbations
47. CVPR 2026WaTeRFlow Watermark Temporal Robustness via Flow Consistency
48. CVPR 2026Your Classifier Can Do More Towards Balancing the Gaps in
49. ICLR 2026A Statistical Learning Perspective on Semi-dual Adversarial Neural Optimal Transport Solvers
50. ICLR 2026AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization

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。