对抗鲁棒论文趋势 2023–2026

对抗样本与防御

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,291 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

对抗鲁棒论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023100796074313
2024131707360334
2025110888544327
202681949349317

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

全部对抗鲁棒论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 1,290 篇，第 12 / 26 页

  1. NeurIPS 2025AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration
  2. NeurIPS 2025Backdoor Mitigation via Invertible Pruning Masks
  3. NeurIPS 2025BAM-ICL: Causal Hijacking In-Context Learning with Budgeted Adversarial Manipulation
  4. NeurIPS 2025Best-of-N Jailbreaking
  5. NeurIPS 2025Better Language Model Inversion by Compactly Representing Next-Token Distributions
  6. NeurIPS 2025Beyond $\tilde{O}(\sqrt{T})$ Constraint Violation for Online Convex Optimization with Adversarial Constraints
  7. NeurIPS 2025Bits Leaked per Query: Information-Theoretic Bounds for Adversarial Attacks on LLMs
  8. NeurIPS 2025Boosting Adversarial Transferability with Spatial Adversarial Alignment
  9. NeurIPS 2025Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness
  10. NeurIPS 2025Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations
  11. NeurIPS 2025CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs
  12. NeurIPS 2025Certifying Deep Network Risks and Individual Predictions with PAC-Bayes Loss via Localized Priors
  13. NeurIPS 2025CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning
  14. NeurIPS 2025Conformal Prediction under Lévy-Prokhorov Distribution Shifts: Robustness to Local and Global Perturbations
  15. NeurIPS 2025Data Selection Matters: Towards Robust Instruction Tuning of Large Multimodal Models
  16. NeurIPS 2025DenoiseRotator: Enhance Pruning Robustness for LLMs via Importance Concentration
  17. NeurIPS 2025DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches
  18. NeurIPS 2025DiffBreak: Is Diffusion-Based Purification Robust?
  19. NeurIPS 2025Diffusion Guided Adversarial State Perturbations in Reinforcement Learning
  20. NeurIPS 2025Distributional Adversarial Attacks and Training in Deep Hedging
  21. NeurIPS 2025Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum
  22. NeurIPS 2025Dynamic Siamese Expansion Framework for Improving Robustness in Online Continual Learning
  23. NeurIPS 2025Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks
  24. NeurIPS 2025E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis
  25. NeurIPS 2025Enhancing CLIP Robustness via Cross-Modality Alignment
  26. NeurIPS 2025Enhancing Graph Classification Robustness with Singular Pooling
  27. NeurIPS 2025Enhancing Visual Prompting through Expanded Transformation Space and Overfitting Mitigation
  28. NeurIPS 2025Evaluating and Learning Optimal Dynamic Treatment Regimes under Truncation by Death
  29. NeurIPS 2025Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction
  30. NeurIPS 2025Exploring the Noise Robustness of Online Conformal Prediction
  31. NeurIPS 2025Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inference
  32. NeurIPS 2025Fit the Distribution: Cross-Image/Prompt Adversarial Attacks on Multimodal Large Language Models
  33. NeurIPS 2025Fortifying Time Series: DTW-Certified Robust Anomaly Detection
  34. NeurIPS 2025FrameShield: Adversarially Robust Video Anomaly Detection
  35. NeurIPS 2025Generative Data Augmentation via Diffusion Distillation, Adversarial Alignment, and Importance Reweighting
  36. NeurIPS 2025Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability
  37. NeurIPS 2025Heterogeneous Adversarial Play in Interactive Environments
  38. NeurIPS 2025HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models
  39. NeurIPS 2025IMPACT: Irregular Multi-Patch Adversarial Composition Based on Two‑Phase Optimization
  40. NeurIPS 2025Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization
  41. NeurIPS 2025Kernel von Mises Formula of the Influence Function
  42. NeurIPS 2025Latent Space Factorization in LoRA
  43. NeurIPS 2025Learning Robust Vision-Language Models from Natural Latent Spaces
  44. NeurIPS 2025LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders
  45. NeurIPS 2025MeCeFO: Enhancing LLM Training Robustness via Fault-Tolerant Optimization
  46. NeurIPS 2025MIBP-Cert: Certified Training against Data Perturbations with Mixed-Integer Bilinear Programs
  47. NeurIPS 2025MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents
  48. NeurIPS 2025MixAT: Combining Continuous and Discrete Adversarial Training for LLMs
  49. NeurIPS 2025Multi-Environment POMDPs: Discrete Model Uncertainty Under Partial Observability
  50. NeurIPS 2025Multimodal Negative Learning

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查对抗鲁棒在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "adversarial-robustness"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「安全与可信」下的其他主题