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 698 篇，第 11 / 14 页

  1. ICML 2024SignSGD with Federated Defense: Harnessing Adversarial Attacks through Gradient Sign Decoding
  2. ICML 2024Split-and-Denoise: Protect large language model inference with local differential privacy
  3. ICML 2024The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks
  4. ICML 2024The Privacy Power of Correlated Noise in Decentralized Learning
  5. ICML 2024Toward Availability Attacks in 3D Point Clouds
  6. ICML 2024Trained Random Forests Completely Reveal your Dataset
  7. ICML 2024Transferable Facial Privacy Protection against Blind Face Restoration via Domain-Consistent Adversarial Obfuscation
  8. ICML 2024Tuning-free Estimation and Inference of Cumulative Distribution Function under Local Differential Privacy
  9. ICML 2024Unveiling Privacy, Memorization, and Input Curvature Links
  10. ICML 2024Verifying message-passing neural networks via topology-based bounds tightening
  11. ICML 2024Watermark Stealing in Large Language Models
  12. NeurIPS 2024A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy
  13. NeurIPS 2024AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attacks
  14. NeurIPS 2024AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
  15. NeurIPS 2024Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections
  16. NeurIPS 2024Attack-Aware Noise Calibration for Differential Privacy
  17. NeurIPS 2024Auditing Privacy Mechanisms via Label Inference Attacks
  18. NeurIPS 2024Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs
  19. NeurIPS 2024Certified Machine Unlearning via Noisy Stochastic Gradient Descent
  20. NeurIPS 2024Continual Counting with Gradual Privacy Expiration
  21. NeurIPS 2024Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature
  22. NeurIPS 2024DAGER: Exact Gradient Inversion for Large Language Models
  23. NeurIPS 2024Data Free Backdoor Attacks
  24. NeurIPS 2024Deep Support Vectors
  25. NeurIPS 2024Differentially Private Set Representations
  26. NeurIPS 2024Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement
  27. NeurIPS 2024Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning
  28. NeurIPS 2024Efficient Adversarial Training in LLMs with Continuous Attacks
  29. NeurIPS 2024Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously
  30. NeurIPS 2024Faster Repeated Evasion Attacks in Tree Ensembles
  31. NeurIPS 2024HEPrune: Fast Private Training of Deep Neural Networks With Encrypted Data Pruning
  32. NeurIPS 2024HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning
  33. NeurIPS 2024Improving Alignment and Robustness with Circuit Breakers
  34. NeurIPS 2024Instance-Optimal Private Density Estimation in the Wasserstein Distance
  35. NeurIPS 2024Instance-Specific Asymmetric Sensitivity in Differential Privacy
  36. NeurIPS 2024Large Language Model Unlearning
  37. NeurIPS 2024MALT Powers Up Adversarial Attacks
  38. NeurIPS 2024Measuring Dejavu Memorization Efficiently
  39. NeurIPS 2024Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
  40. NeurIPS 2024Membership Inference Attacks against Large Vision-Language Models
  41. NeurIPS 2024MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models
  42. NeurIPS 2024Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
  43. NeurIPS 2024On Differentially Private Subspace Estimation in a Distribution-Free Setting
  44. NeurIPS 2024On provable privacy vulnerabilities of graph representations
  45. NeurIPS 2024OSLO: One-Shot Label-Only Membership Inference Attacks
  46. NeurIPS 2024PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
  47. NeurIPS 2024Prior-itizing Privacy: A Bayesian Approach to Setting the Privacy Budget in Differential Privacy
  48. NeurIPS 2024Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
  49. NeurIPS 2024Private and Personalized Frequency Estimation in a Federated Setting
  50. NeurIPS 2024PrivAuditor: Benchmarking Data Protection Vulnerabilities in LLM Adaptation Techniques

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