差分隐私论文趋势 2023–2026

主要结论

• 差分隐私论文从 2023 年的 117 篇降到 2026 年的 103 篇，热度在回落。
• NeurIPS 是发差分隐私论文最多的会议，2023–2026 年共 217 篇，占四个会议总量的 45%。
• 交叉方向里涨得最快的是社会层面 · accountability transparency and interpretability：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 22 篇。
• 在「联邦与隐私」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的安全聚合是 1.8 倍，差分隐私是 0.9 倍。

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

• NeurIPS 2026A Unified Framework for Adversary-Aware Differential Privacy Bounds
• ICML 2026Optimal conversion from Rényi Differential Privacy to $f$-Differential Privacy
• ICLR 2026Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models
• CVPR 2026Fully Decentralized Certified Unlearning
• NeurIPS 2025Continual Release Moment Estimation with Differential Privacy
• ICML 2025Leveraging Per-Instance Privacy for Machine Unlearning
• ICLR 2025Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning
• CVPR 2025Focal Split: Untethered Snapshot Depth from Differential Defocus
• NeurIPS 2024$\texttt{pfl-research}$: simulation framework for accelerating research in Private Federated Learning
• ICML 2024Delving into Differentially Private Transformer
• ICLR 2024Decoupled Marked Temporal Point Process using Neural Ordinary Differential Equations
• CVPR 2024Affine Equivariant Networks Based on Differential Invariants
• NeurIPS 2023(Amplified) Banded Matrix Factorization: A unified approach to private training
• ICML 2023Bayesian Estimation of Differential Privacy
• ICLR 2023A Statistical Framework for Personalized Federated Learning and Estimation: Theory, Algorithms, and Privacy
• CVPR 2023Learning To Generate Image Embeddings With User-Level Differential Privacy
• NeurIPS 2026Asymptotically Optimal Best Arm Identification with Fixed-Budget under Differential Privacy
• ICML 2026Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov–Arnold Networks
• ICLR 2026Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy
• CVPR 2026LDP-Slicing Local Differential Privacy for Images via Randomized Bit-Plane Slicing

全部差分隐私论文

共 66 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 2025Adaptive Data Analysis for Growing Data
4. NeurIPS 2025Adaptive Sigmoid Clipping for Balancing the Direction–Magnitude Mismatch Trade-off in Differentially Private Learning
5. NeurIPS 2025An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise
6. NeurIPS 2025Blameless Users in a Clean Room: Defining Copyright Protection for Generative Models
7. NeurIPS 2025Boundary-Value PDEs Meet Higher-Order Differential Topology-aware GNNs
8. NeurIPS 2025Collapsing Taylor Mode Automatic Differentiation
9. NeurIPS 2025Continual Release Moment Estimation with Differential Privacy
10. NeurIPS 2025Continuous Simplicial Neural Networks
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 2025Dense Metric Depth Estimation via Event-based Differential Focus Volume Prompting
14. NeurIPS 2025Differential Privacy for Euclidean Jordan Algebra with Applications to Private Symmetric Cone Programming
15. NeurIPS 2025Differential Privacy on Fully Dynamic Streams
16. NeurIPS 2025Differentially Private Bilevel Optimization: Efficient Algorithms with Near-Optimal Rates
17. NeurIPS 2025Differentially Private Federated Low Rank Adaptation Beyond Fixed-Matrix
18. NeurIPS 2025Differentially Private Gomory-Hu Trees
19. NeurIPS 2025Differentially Private High-dimensional Variable Selection via Integer Programming
20. NeurIPS 2025Differentially Private Quantiles with Smaller Error
21. NeurIPS 2025Differentially Private Relational Learning with Entity-level Privacy Guarantees
22. NeurIPS 2025DIFFSSR: Stereo Image Super-resolution Using Differential Transformer
23. NeurIPS 2025Discovering Symbolic Partial Differential Equation by Abductive Learning
24. NeurIPS 2025Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data
25. NeurIPS 2025FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA
26. NeurIPS 2025GeoClip: Geometry-Aware Clipping for Differentially Private SGD
27. NeurIPS 2025How Well Can Differential Privacy Be Audited in One Run?
28. NeurIPS 2025Instance-Optimality for Private KL Distribution Estimation
29. NeurIPS 2025Learning Differential Pyramid Representation for Tone Mapping
30. NeurIPS 2025Locally Optimal Private Sampling: Beyond the Global Minimax
31. NeurIPS 2025Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy
32. NeurIPS 2025Multi-Class Support Vector Machine with Differential Privacy
33. NeurIPS 2025Nearly-Linear Time Private Hypothesis Selection with the Optimal Approximation Factor
34. NeurIPS 2025Neural Fractional Attention Differential Equations
35. NeurIPS 2025On Traceability in $\ell_p$ Stochastic Convex Optimization
36. NeurIPS 2025Online Locally Differentially Private Conformal Prediction via Binary Inquiries
37. NeurIPS 2025Online robust locally differentially private learning for nonparametric regression
38. NeurIPS 2025Optimal Best Arm Identification under Differential Privacy
39. NeurIPS 2025Optimal Regret of Bandits under Differential Privacy
40. NeurIPS 2025PREAMBLE: Private and Efficient Aggregation via Block Sparse Vectors
41. NeurIPS 2025Privacy amplification by random allocation
42. NeurIPS 2025Private Continual Counting of Unbounded Streams
43. NeurIPS 2025Private Evolution Converges
44. NeurIPS 2025Private Geometric Median in Nearly-Linear Time
45. NeurIPS 2025Private Hyperparameter Tuning with Ex-Post Guarantee
46. NeurIPS 2025Private Online Learning against an Adaptive Adversary: Realizable and Agnostic Settings
47. NeurIPS 2025Private Set Union with Multiple Contributions
48. NeurIPS 2025Private Statistical Estimation via Truncation
49. NeurIPS 2025Private Training Large-scale Models with Efficient DP-SGD
50. NeurIPS 2025Private Zeroth-Order Optimization with Public Data

常见问题

2023–2026 年四大会议一共有多少篇差分隐私论文？

共 479 篇，按年份分别是 2023 年 117 篇、2024 年 113 篇、2025 年 146 篇、2026 年 103 篇。

NeurIPS 2026 有多少篇差分隐私论文？

NeurIPS 2026 有 23 篇差分隐私论文，上一届是 66 篇。

ICLR 2026 有多少篇差分隐私论文？

ICLR 2026 有 31 篇差分隐私论文，上一届是 29 篇。

ICML 2026 有多少篇差分隐私论文？

ICML 2026 有 42 篇差分隐私论文，上一届是 47 篇。

CVPR 2026 有多少篇差分隐私论文？

CVPR 2026 有 7 篇差分隐私论文，上一届是 4 篇。

哪个会议的差分隐私论文最多？

NeurIPS，2023–2026 年共 217 篇。