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 8 / 26 页

351. CVPR 2025Stop Walking in Circles! Bailing Out Early in Projected Gradient Descent
352. CVPR 2025T-CIL: Temperature Scaling using Adversarial Perturbation for Calibration in Class-Incremental Learning
353. CVPR 2025TAET: Two-Stage Adversarial Equalization Training on Long-Tailed Distributions
354. CVPR 2025TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models
355. CVPR 2025TAROT: Towards Essentially Domain-Invariant Robustness with Theoretical Justification
356. CVPR 2025Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems
357. CVPR 2025Tightening Robustness Verification of MaxPool-based Neural Networks via Minimizing the Over-Approximation Zone
358. CVPR 2025Towards Effective and Sparse Adversarial Attack on Spiking Neural Networks via Breaking Invisible Surrogate Gradients
359. CVPR 2025Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks
360. CVPR 2025Weakly Supervised Contrastive Adversarial Training for Learning Robust Features from Semi-supervised Data
361. ICLR 2025$\sigma$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples
362. ICLR 2025ADBM: Adversarial Diffusion Bridge Model for Reliable Adversarial Purification
363. ICLR 2025Adversarial Attacks on Data Attribution
364. ICLR 2025Adversarial Latent Feature Augmentation for Fairness
365. ICLR 2025Adversarial Machine Unlearning
366. ICLR 2025Adversarial Mixup Unlearning
367. ICLR 2025Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI
368. ICLR 2025Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step
369. ICLR 2025Adversarial Search Engine Optimization for Large Language Models
370. ICLR 2025Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data
371. ICLR 2025Adversarial Training for Defense Against Label Poisoning Attacks
372. ICLR 2025Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized Embeddings
373. ICLR 2025Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness
374. ICLR 2025AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption
375. ICLR 2025AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
376. ICLR 2025Algorithmic Stability Based Generalization Bounds for Adversarial Training
377. ICLR 2025Aligned LLMs Are Not Aligned Browser Agents
378. ICLR 2025Artificial Kuramoto Oscillatory Neurons
379. ICLR 2025ASTrA: Adversarial Self-supervised Training with Adaptive-Attacks
380. ICLR 2025Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness
381. ICLR 2025Boosting the visual interpretability of CLIP via adversarial fine-tuning
382. ICLR 2025Certified Robustness Under Bounded Levenshtein Distance
383. ICLR 2025CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification
384. ICLR 2025Confidence Elicitation: A New Attack Vector for Large Language Models
385. ICLR 2025Deep MMD Gradient Flow without adversarial training
386. ICLR 2025Democratic Training Against Universal Adversarial Perturbations
387. ICLR 2025Diffusion State-Guided Projected Gradient for Inverse Problems
388. ICLR 2025Dissecting Adversarial Robustness of Multimodal LM Agents
389. ICLR 2025Does Refusal Training in LLMs Generalize to the Past Tense?
390. ICLR 2025DRoP: Distributionally Robust Data Pruning
391. ICLR 2025Endless Jailbreaks with Bijection Learning
392. ICLR 2025Endowing Visual Reprogramming with Adversarial Robustness
393. ICLR 2025Enhancing Prediction Performance through Influence Measure
394. ICLR 2025Enhancing Robust Fairness via Confusional Spectral Regularization
395. ICLR 2025Estimating the Probabilities of Rare Outputs in Language Models
396. ICLR 2025Exact Certification of (Graph) Neural Networks Against Label Poisoning
397. ICLR 2025Exploring The Forgetting in Adversarial Training: A Novel Method for Enhancing Robustness
398. ICLR 2025Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
399. ICLR 2025Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks
400. ICLR 2025GOttack: Universal Adversarial Attacks on Graph Neural Networks via Graph Orbits Learning

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。