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 180 篇，第 4 / 4 页

  1. NeurIPS 2024OSLO: One-Shot Label-Only Membership Inference Attacks
  2. NeurIPS 2024PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
  3. NeurIPS 2024Prior-itizing Privacy: A Bayesian Approach to Setting the Privacy Budget in Differential Privacy
  4. NeurIPS 2024Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
  5. NeurIPS 2024Private and Personalized Frequency Estimation in a Federated Setting
  6. NeurIPS 2024PrivAuditor: Benchmarking Data Protection Vulnerabilities in LLM Adaptation Techniques
  7. NeurIPS 2024PrivCirNet: Efficient Private Inference via Block Circulant Transformation
  8. NeurIPS 2024Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models
  9. NeurIPS 2024Pseudo-Private Data Guided Model Inversion Attacks
  10. NeurIPS 2024RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees
  11. NeurIPS 2024Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
  12. NeurIPS 2024Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
  13. NeurIPS 2024RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation
  14. NeurIPS 2024Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
  15. NeurIPS 2024Scalable DP-SGD: Shuffling vs. Poisson Subsampling
  16. NeurIPS 2024Scanning Trojaned Models Using Out-of-Distribution Samples
  17. NeurIPS 2024SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents
  18. NeurIPS 2024SPEAR: Exact Gradient Inversion of Batches in Federated Learning
  19. NeurIPS 2024Stealth edits to large language models
  20. NeurIPS 2024SuperDeepFool: a new fast and accurate minimal adversarial attack
  21. NeurIPS 2024TARP-VP: Towards Evaluation of Transferred Adversarial Robustness and Privacy on Label Mapping Visual Prompting Models
  22. NeurIPS 2024The Limits of Differential Privacy in Online Learning
  23. NeurIPS 2024Trap-MID: Trapdoor-based Defense against Model Inversion Attacks
  24. NeurIPS 2024Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
  25. NeurIPS 2024Unelicitable Backdoors via Cryptographic Transformer Circuits
  26. NeurIPS 2024United We Stand, Divided We Fall: Fingerprinting Deep Neural Networks via Adversarial Trajectories
  27. NeurIPS 2024Watermarking Makes Language Models Radioactive
  28. NeurIPS 2024WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks
  29. NeurIPS 2024Wide Two-Layer Networks can Learn from Adversarial Perturbations
  30. NeurIPS 2024WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models

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