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 70 篇，第 1 / 2 页

1. ICLR 2024A Recipe for Improved Certifiable Robustness
2. ICLR 2024A ROBUST DIFFERENTIAL NEURAL ODE OPTIMIZER
3. ICLR 2024A Sublinear Adversarial Training Algorithm
4. ICLR 2024Adversarial Attacks on Fairness of Graph Neural Networks
5. ICLR 2024Adversarial AutoMixup
6. ICLR 2024Adversarial Feature Map Pruning for Backdoor
7. ICLR 2024Adversarial Imitation Learning via Boosting
8. ICLR 2024Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization
9. ICLR 2024Adversarial Training Should Be Cast as a Non-Zero-Sum Game
10. ICLR 2024An Efficient Tester-Learner for Halfspaces
11. ICLR 2024An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language Models
12. ICLR 2024An LLM can Fool Itself: A Prompt-Based Adversarial Attack
13. ICLR 2024Analyzing and Improving Optimal-Transport-based Adversarial Networks
14. ICLR 2024Annealing Self-Distillation Rectification Improves Adversarial Training
15. ICLR 2024AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
16. ICLR 2024AutoLoRa: An Automated Robust Fine-Tuning Framework
17. ICLR 2024Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations
18. ICLR 2024Boosting the Adversarial Robustness of Graph Neural Networks: An OOD Perspective
19. ICLR 2024Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks
20. ICLR 2024BRUSLEATTACK: A QUERY-EFFICIENT SCORE- BASED BLACK-BOX SPARSE ADVERSARIAL ATTACK
21. ICLR 2024Certified Adversarial Robustness for Rate Encoded Spiking Neural Networks
22. ICLR 2024COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits
23. ICLR 2024Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training
24. ICLR 2024Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit
25. ICLR 2024DAFA: Distance-Aware Fair Adversarial Training
26. ICLR 2024Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Search
27. ICLR 2024Doubly Robust Instance-Reweighted Adversarial Training
28. ICLR 2024DP-SGD Without Clipping: The Lipschitz Neural Network Way
29. ICLR 2024DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness
30. ICLR 2024Efficient local linearity regularization to overcome catastrophic overfitting
31. ICLR 2024Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches
32. ICLR 2024Evaluating the Zero-shot Robustness of Instruction-tuned Language Models
33. ICLR 2024Expressive Losses for Verified Robustness via Convex Combinations
34. ICLR 2024Expressivity of ReLU-Networks under Convex Relaxations
35. ICLR 2024Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
36. ICLR 2024GNNCert: Deterministic Certification of Graph Neural Networks against Adversarial Perturbations
37. ICLR 2024Incremental Randomized Smoothing Certification
38. ICLR 2024Input-gradient space particle inference for neural network ensembles
39. ICLR 2024Interpreting Robustness Proofs of Deep Neural Networks
40. ICLR 2024IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks
41. ICLR 2024Label-Noise Robust Diffusion Models
42. ICLR 2024Large Language Models Are Not Robust Multiple Choice Selectors
43. ICLR 2024Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds
44. ICLR 2024LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
45. ICLR 2024Mitigating Emergent Robustness Degradation while Scaling Graph Learning
46. ICLR 2024Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing
47. ICLR 2024On Adversarial Training without Perturbing all Examples
48. ICLR 2024On the Vulnerability of Adversarially Trained Models Against Two-faced Attacks
49. ICLR 2024Optimal transport based adversarial patch to leverage large scale attack transferability
50. ICLR 2024Out-Of-Domain Unlabeled Data Improves Generalization

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。