社会层面 · privacy论文趋势 2023–2026

AI 社会议题：privacy

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 431 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

社会层面 · privacy论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023457521
20248711136117
2025802712155
2026442902138

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

全部社会层面 · privacy论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 431 篇，第 6 / 9 页

  1. NeurIPS 2025Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy
  2. NeurIPS 2025MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM Inference
  3. NeurIPS 2025Multi-Class Support Vector Machine with Differential Privacy
  4. NeurIPS 2025OASIS: One-Shot Federated Graph Learning via Wasserstein Assisted Knowledge Integration
  5. NeurIPS 2025ObCLIP: Oblivious CLoud-Device Hybrid Image Generation with Privacy Preservation
  6. NeurIPS 2025On the Sample Complexity of Differentially Private Policy Optimization
  7. NeurIPS 2025OpenGU: A Comprehensive Benchmark for Graph Unlearning
  8. NeurIPS 2025Optimal Best Arm Identification under Differential Privacy
  9. NeurIPS 2025Optimal Regret of Bandits under Differential Privacy
  10. NeurIPS 2025Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models
  11. NeurIPS 2025Practical Bayes-Optimal Membership Inference Attacks
  12. NeurIPS 2025Privacy amplification by random allocation
  13. NeurIPS 2025Privacy Reasoning in Ambiguous Contexts
  14. NeurIPS 2025Private Continual Counting of Unbounded Streams
  15. NeurIPS 2025Private Geometric Median in Nearly-Linear Time
  16. NeurIPS 2025Private Hyperparameter Tuning with Ex-Post Guarantee
  17. NeurIPS 2025Private Set Union with Multiple Contributions
  18. NeurIPS 2025Private Zeroth-Order Optimization with Public Data
  19. NeurIPS 2025Probabilistic Reasoning with LLMs for Privacy Risk Estimation
  20. NeurIPS 2025Purifying Approximate Differential Privacy with Randomized Post-processing
  21. NeurIPS 2025Query-Efficient Locally Private Hypothesis Selection via the Scheffe Graph
  22. NeurIPS 2025Rethinking Fair Federated Learning from Parameter and Client View
  23. NeurIPS 2025Rethinking the Role of Verbatim Memorization in LLM Privacy
  24. NeurIPS 2025Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions
  25. NeurIPS 2025RUAGO: Effective and Practical Retain-Free Unlearning via Adversarial Attack and OOD Generator
  26. NeurIPS 2025Second-Order Convergence in Private Stochastic Non-Convex Optimization
  27. NeurIPS 2025Secure and Confidential Certificates of Online Fairness
  28. NeurIPS 2025Sequentially Auditing Differential Privacy
  29. NeurIPS 2025Setting $\varepsilon$ is not the Issue in Differential Privacy
  30. NeurIPS 2025Sketched Gaussian Mechanism for Private Federated Learning
  31. NeurIPS 2025Subgraph Federated Learning via Spectral Methods
  32. NeurIPS 2025Sum Estimation under Personalized Local Differential Privacy
  33. NeurIPS 2025Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries
  34. NeurIPS 2025The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples
  35. NeurIPS 2025Time-uniform and Asymptotic Confidence Sequence of Quantile under Local Differential Privacy
  36. NeurIPS 2025TokenSwap: A Lightweight Method to Disrupt Memorized Sequences in LLMs
  37. NeurIPS 2025Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
  38. NeurIPS 2025Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks
  39. NeurIPS 2025Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy
  40. NeurIPS 2025Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
  41. NeurIPS 2025Versatile Transferable Unlearnable Example Generator
  42. NeurIPS 2025⁠When Data Can't Meet: Estimating Correlation Across Privacy Barriers
  43. NeurIPS 2025You Only Communicate Once: One-shot Federated Low-Rank Adaptation of MLLM
  44. CVPR 2024DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection
  45. CVPR 2024Efficient Privacy-Preserving Visual Localization Using 3D Ray Clouds
  46. CVPR 2024FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning
  47. CVPR 2024Privacy-Preserving Face Recognition Using Trainable Feature Subtraction
  48. CVPR 2024Privacy-Preserving Optics for Enhancing Protection in Face De-Identification
  49. CVPR 2024Validating Privacy-Preserving Face Recognition under a Minimum Assumption
  50. ICLR 2024Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion 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 查社会层面 · privacy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": "social-privacy"}

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社会层面 · privacy论文？
共 431 篇，按年份分别是 2023 年 21 篇、2024 年 117 篇、2025 年 155 篇、2026 年 138 篇。
NeurIPS 2026 有多少篇社会层面 · privacy论文？
NeurIPS 2026 有 44 篇社会层面 · privacy论文，上一届是 80 篇。
ICLR 2026 有多少篇社会层面 · privacy论文？
ICLR 2026 有 2 篇社会层面 · privacy论文，上一届是 2 篇。
ICML 2026 有多少篇社会层面 · privacy论文？
ICML 2026 有 90 篇社会层面 · privacy论文，上一届是 71 篇。
CVPR 2026 有多少篇社会层面 · privacy论文？
CVPR 2026 有 2 篇社会层面 · privacy论文，上一届是 2 篇。
哪个会议的社会层面 · privacy论文最多？
NeurIPS，2023–2026 年共 215 篇。

「对齐与负责任 AI」下的其他主题