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 80 篇，第 1 / 2 页

  1. NeurIPS 2025A Generalized Binary Tree Mechanism for Private Approximation of All-Pair Shortest Distances
  2. NeurIPS 2025A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable Input
  3. NeurIPS 2025A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation
  4. NeurIPS 2025Adaptive Data Analysis for Growing Data
  5. NeurIPS 2025Adaptive Sigmoid Clipping for Balancing the Direction–Magnitude Mismatch Trade-off in Differentially Private Learning
  6. NeurIPS 2025AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents
  7. NeurIPS 2025An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise
  8. NeurIPS 2025Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools
  9. NeurIPS 2025Can We Infer Confidential Properties of Training Data from LLMs?
  10. NeurIPS 2025Continual Release Moment Estimation with Differential Privacy
  11. NeurIPS 2025Controlling The Spread of Epidemics on Networks with Differential Privacy
  12. NeurIPS 2025Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy
  13. NeurIPS 2025CryptoMoE: Privacy-Preserving and Scalable Mixture of Experts Inference via Balanced Expert Routing
  14. NeurIPS 2025Data-Free Model Extraction for Black-box Recommender Systems via Graph Convolutions
  15. NeurIPS 2025Deep Learning with Plausible Deniability
  16. NeurIPS 2025DictPFL: Efficient and Private Federated Learning on Encrypted Gradients
  17. NeurIPS 2025Differential Privacy for Euclidean Jordan Algebra with Applications to Private Symmetric Cone Programming
  18. NeurIPS 2025Differential Privacy on Fully Dynamic Streams
  19. NeurIPS 2025Differentially Private Bilevel Optimization: Efficient Algorithms with Near-Optimal Rates
  20. NeurIPS 2025Differentially Private Gomory-Hu Trees
  21. NeurIPS 2025Differentially Private High-dimensional Variable Selection via Integer Programming
  22. NeurIPS 2025Differentially Private Quantiles with Smaller Error
  23. NeurIPS 2025Differentially Private Relational Learning with Entity-level Privacy Guarantees
  24. NeurIPS 2025DKDR: Dynamic Knowledge Distillation for Reliability in Federated Learning
  25. NeurIPS 2025Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data
  26. NeurIPS 2025DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents
  27. NeurIPS 2025Exploring the limits of strong membership inference attacks on large language models
  28. NeurIPS 2025FedRW: Efficient Privacy-Preserving Data Reweighting for Enhancing Federated Learning of Language Models
  29. NeurIPS 2025FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts
  30. NeurIPS 2025FracFace: Breaking The Visual Clues—Fractal-Based Privacy-Preserving Face Recognition
  31. NeurIPS 2025GeoClip: Geometry-Aware Clipping for Differentially Private SGD
  32. NeurIPS 2025Harnessing the Universal Geometry of Embeddings
  33. NeurIPS 2025How Well Can Differential Privacy Be Audited in One Run?
  34. NeurIPS 2025Instance-Optimality for Private KL Distribution Estimation
  35. NeurIPS 2025InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy
  36. NeurIPS 2025Locally Optimal Private Sampling: Beyond the Global Minimax
  37. NeurIPS 2025Machine Unlearning via Task Simplex Arithmetic
  38. NeurIPS 2025Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy
  39. NeurIPS 2025MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM Inference
  40. NeurIPS 2025Multi-Class Support Vector Machine with Differential Privacy
  41. NeurIPS 2025OASIS: One-Shot Federated Graph Learning via Wasserstein Assisted Knowledge Integration
  42. NeurIPS 2025ObCLIP: Oblivious CLoud-Device Hybrid Image Generation with Privacy Preservation
  43. NeurIPS 2025On the Sample Complexity of Differentially Private Policy Optimization
  44. NeurIPS 2025OpenGU: A Comprehensive Benchmark for Graph Unlearning
  45. NeurIPS 2025Optimal Best Arm Identification under Differential Privacy
  46. NeurIPS 2025Optimal Regret of Bandits under Differential Privacy
  47. NeurIPS 2025Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models
  48. NeurIPS 2025Practical Bayes-Optimal Membership Inference Attacks
  49. NeurIPS 2025Privacy amplification by random allocation
  50. NeurIPS 2025Privacy Reasoning in Ambiguous Contexts

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