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 311 篇，第 1 / 7 页

1. ICML 2026``Someone Hid It!'': Query-Agnostic Black-Box Attacks on LLM-Based Retrieval
2. ICML 2026A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness
3. ICML 2026Adaptive Probe-based Steering for Robust LLM Jailbreaking
4. ICML 2026Adaptively Robust Resettable Streaming
5. ICML 2026Adversarial Attacks and Robust Training for Hypergraph Neural Networks
6. ICML 2026Adversarial Robustness of Implicit Neural Representation-Based Classifiers
7. ICML 2026Adversarial Vulnerability from Interference Between Features in Superposition
8. ICML 2026AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing
9. ICML 2026Benign Overfitting in Adversarial Training for Vision Transformers
10. ICML 2026Bias in Zeroth-Order Normal Estimation for Decision-Based Attacks
11. ICML 2026BiRQA: Bidirectional Robust Quality Assessment for Images
12. ICML 2026BOCLOAK: Optimal Transport-Guided Adversarial Attacks on Graph Neural Network-Based Bot Detection
13. ICML 2026Budget-Efficient Attacks and Robustness Training for Cooperative MARL
14. ICML 2026Bulk-Calibrated Credal Ambiguity Sets: Fast, Tractable Decision Making under Out-of-Sample Contamination
15. ICML 2026Calibrating Uncertainty for Zero-Shot Adversarial CLIP
16. ICML 2026CaliDist: Calibrating Large Language Models via Behavioral Robustness to Distraction
17. ICML 2026Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing
18. ICML 2026Certifying Graph Neural Networks Against Label and Structure Poisoning
19. ICML 2026Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP
20. ICML 2026CORE: Context-Robust Remasking for Diffusion Language Models
21. ICML 2026Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates
22. ICML 2026DART: Distribution-Aware Adaptive Relational Transfer for Adversarial Attacks against Closed-Source MLLMs
23. ICML 2026DDGA: Dirichlet Distributional Gradient Aggregation for Transferable Vision-Language Adversarial Attacks
24. ICML 2026DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers
25. ICML 2026Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment
26. ICML 2026Distributionally Robust Markov Games with Average Reward
27. ICML 2026Does a Hybrid Space-Aware Randomized Defense Improve Empirical and Certified Adversarial Robustness?
28. ICML 2026Dual-branch Robust Unlearnable Examples
29. ICML 2026Enhanced Latent-Space Adversarial Training for Super-Resolution
30. ICML 2026Feature Collapse Under Corruption: An Entropy Perspective on Robust Neural Networks
31. ICML 2026Fingerprinting Pre-trained Encoders under Arbitrary Downstream Fine-Tuning via Adversarial Shifting
32. ICML 2026From Internal Diagnosis to External Auditing: A VLM-Driven Paradigm for Data-Free Online Backdoor Defense
33. ICML 2026Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation Recognition
34. ICML 2026Harnessing Non-Adversarial Robustness in Large Language Models
35. ICML 2026Hearing Without Noticing? Attention-Aware Stealthy Black-Box Adversarial Audio Attacks
36. ICML 2026High-Dimensional Sensitivity Analysis for Genomic Studies: An Adversarial Framework for Learning Worst-Case Latent Confounders
37. ICML 2026Higher-Order Certified Robustness for Regression
38. ICML 2026Identifiable Smooth Conjugacy Learning via Adversarial Orthogonality
39. ICML 2026Improving Adversarial Robustness of Attribution via Implicit Regularization
40. ICML 2026Improving the Robustness-Utility Trade-off in Decentralized Learning over Sparse Networks
41. ICML 2026Improving the Sensitivity of Backdoor Detectors via Class Subspace Orthogonalization
42. ICML 2026Learning to Emulate Chaos: Adversarial Optimal Transport Regularization
43. ICML 2026Localize and Neutralize: Gradient-Guided Token Suppression Against Visual Prompt Injection Attack
44. ICML 2026Logit Distance Bounds Representational Similarity
45. ICML 2026MaMa: A Game-Theoretic Approach for Designing Safe Agentic Systems
46. ICML 2026MEDUSA: Motion Elimination in Diffusion Using Spectral Attack
47. ICML 2026Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust?
48. ICML 2026MoCo-EA: Exploiting Adversarial Mode Connectivity for Efficient Evolutionary Attacks
49. ICML 2026Near-Minimax Multi-Objective RL under Predictable Adversarial Preferences and Preference-Free Exploration in Linear MDPs
50. ICML 2026Non-Parametric Probabilistic Robustness: A Conservative Risk Estimator under Unknown Perturbation Distributions

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。