隐私攻击论文趋势 2023–2026

成员推断等

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 698 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

隐私攻击论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202346242925124
202463534222180
202545832918175
2026551023824219

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

全部隐私攻击论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 83 篇，第 2 / 2 页

  1. ICLR 2025Optimality of Matrix Mechanism on $\ell_p^p$-metric
  2. ICLR 2025Persistent Pre-training Poisoning of LLMs
  3. ICLR 2025PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models
  4. ICLR 2025Privacy Auditing of Large Language Models
  5. ICLR 2025Privacy-Aware Lifelong Learning
  6. ICLR 2025Privacy-Preserving Personalized Federated Prompt Learning for Multimodal Large Language Models
  7. ICLR 2025Privately Counting Partially Ordered Data
  8. ICLR 2025Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility
  9. ICLR 2025ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs
  10. ICLR 2025Protecting against simultaneous data poisoning attacks
  11. ICLR 2025Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
  12. ICLR 2025REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
  13. ICLR 2025RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
  14. ICLR 2025Scalable Extraction of Training Data from Aligned, Production Language Models
  15. ICLR 2025SelectFormer in Data Markets: Privacy-Preserving and Efficient Data Selection for Transformers with Multi-Party Computation
  16. ICLR 2025SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters
  17. ICLR 2025Singular Subspace Perturbation Bounds via Rectangular Random Matrix Diffusions
  18. ICLR 2025Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion Attacks
  19. ICLR 2025Stochastic Bandits Robust to Adversarial Attacks
  20. ICLR 2025Support is All You Need for Certified VAE Training
  21. ICLR 2025Tamper-Resistant Safeguards for Open-Weight LLMs
  22. ICLR 2025Targeted Attack Improves Protection against Unauthorized Diffusion Customization
  23. ICLR 2025The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
  24. ICLR 2025Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
  25. ICLR 2025To Tackle Adversarial Transferability: A Novel Ensemble Training Method with Fourier Transformation
  26. ICLR 2025Towards Certification of Uncertainty Calibration under Adversarial Attacks
  27. ICLR 2025Tracking the Copyright of Large Vision-Language Models through Parameter Learning Adversarial Images
  28. ICLR 2025Training Robust Ensembles Requires Rethinking Lipschitz Continuity
  29. ICLR 2025Understanding and Enhancing the Transferability of Jailbreaking Attacks
  30. ICLR 2025Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
  31. ICLR 2025Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
  32. ICLR 2025Variational Best-of-N Alignment
  33. ICLR 2025Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks

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 查隐私攻击在 ICLR 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": "privacy-attacks"}

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隐私攻击论文？
共 698 篇，按年份分别是 2023 年 124 篇、2024 年 180 篇、2025 年 175 篇、2026 年 219 篇。
NeurIPS 2026 有多少篇隐私攻击论文？
NeurIPS 2026 有 55 篇隐私攻击论文，上一届是 45 篇。
ICLR 2026 有多少篇隐私攻击论文？
ICLR 2026 有 102 篇隐私攻击论文，上一届是 83 篇。
ICML 2026 有多少篇隐私攻击论文？
ICML 2026 有 38 篇隐私攻击论文，上一届是 29 篇。
CVPR 2026 有多少篇隐私攻击论文？
CVPR 2026 有 24 篇隐私攻击论文，上一届是 18 篇。
哪个会议的隐私攻击论文最多？
ICLR，2023–2026 年共 262 篇。

「联邦与隐私」下的其他主题