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 7 / 9 页

301. NeurIPS 2024Stability and Generalization of Adversarial Training for Shallow Neural Networks with Smooth Activation
302. NeurIPS 2024Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack
303. NeurIPS 2024SuperDeepFool: a new fast and accurate minimal adversarial attack
304. NeurIPS 2024TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases
305. NeurIPS 2024Taming Heavy-Tailed Losses in Adversarial Bandits and the Best-of-Both-Worlds Setting
306. NeurIPS 2024Target-Guided Adversarial Point Cloud Transformer Towards Recognition Against Real-world Corruptions
307. NeurIPS 2024TARP-VP: Towards Evaluation of Transferred Adversarial Robustness and Privacy on Label Mapping Visual Prompting Models
308. NeurIPS 2024Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models
309. NeurIPS 2024The Group Robustness is in the Details: Revisiting Finetuning under Spurious Correlations
310. NeurIPS 2024The Implicit Bias of Gradient Descent toward Collaboration between Layers: A Dynamic Analysis of Multilayer Perceptions
311. NeurIPS 2024The Price of Implicit Bias in Adversarially Robust Generalization
312. NeurIPS 2024The Secretary Problem with Predicted Additive Gap
313. NeurIPS 2024Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness
314. NeurIPS 2024Transferable Adversarial Attacks on SAM and Its Downstream Models
315. NeurIPS 2024Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness
316. NeurIPS 2024Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions
317. NeurIPS 2024Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation
318. NeurIPS 2024United We Stand, Divided We Fall: Fingerprinting Deep Neural Networks via Adversarial Trajectories
319. NeurIPS 2024Unveiling the Potential of Robustness in Selecting Conditional Average Treatment Effect Estimators
320. NeurIPS 2024WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off
321. NeurIPS 2024Weight for Robustness: A Comprehensive Approach towards Optimal Fault-Tolerant Asynchronous ML
322. NeurIPS 2024Wide Two-Layer Networks can Learn from Adversarial Perturbations
323. NeurIPS 2023A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)
324. NeurIPS 2023Adversarial Examples Are Not Real Features
325. NeurIPS 2023Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces
326. NeurIPS 2023Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness
327. NeurIPS 2023Adversarial Learning for Feature Shift Detection and Correction
328. NeurIPS 2023Adversarial Resilience in Sequential Prediction via Abstention
329. NeurIPS 2023Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach
330. NeurIPS 2023Adversarial Robustness through Random Weight Sampling
331. NeurIPS 2023Adversarial Self-Training Improves Robustness and Generalization for Gradual Domain Adaptation
332. NeurIPS 2023Adversarial Training from Mean Field Perspective
333. NeurIPS 2023AND: Adversarial Neural Degradation for Learning Blind Image Super-Resolution
334. NeurIPS 2023Asymmetric Certified Robustness via Feature-Convex Neural Networks
335. NeurIPS 2023Asynchronous Proportional Response Dynamics: Convergence in Markets with Adversarial Scheduling
336. NeurIPS 2023Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective
337. NeurIPS 2023Batchnorm Allows Unsupervised Radial Attacks
338. NeurIPS 2023Benchmarking Robustness to Adversarial Image Obfuscations
339. NeurIPS 2023Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense
340. NeurIPS 2023Blurred-Dilated Method for Adversarial Attacks
341. NeurIPS 2023Boosting Adversarial Transferability by Achieving Flat Local Maxima
342. NeurIPS 2023Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits
343. NeurIPS 2023CamoPatch: An Evolutionary Strategy for Generating Camoflauged Adversarial Patches
344. NeurIPS 2023Certifiably Robust Graph Contrastive Learning
345. NeurIPS 2023Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization
346. NeurIPS 2023Characterizing the Optimal $0-1$ Loss for Multi-class Classification with a Test-time Attacker
347. NeurIPS 2023Color Equivariant Convolutional Networks
348. NeurIPS 2023Connecting Certified and Adversarial Training
349. NeurIPS 2023Content-based Unrestricted Adversarial Attack
350. NeurIPS 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT 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。