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 67 篇，第 1 / 2 页

1. NeurIPS 2023(Amplified) Banded Matrix Factorization: A unified approach to private training
2. NeurIPS 2023$k$-Means Clustering with Distance-Based Privacy
3. NeurIPS 2023A Privacy-Friendly Approach to Data Valuation
4. NeurIPS 2023A Randomized Approach to Tight Privacy Accounting
5. NeurIPS 2023A Smooth Binary Mechanism for Efficient Private Continual Observation
6. NeurIPS 2023A Unified Fast Gradient Clipping Framework for DP-SGD
7. NeurIPS 2023Adaptive Data Analysis in a Balanced Adversarial Model
8. NeurIPS 2023Adaptive Privacy Composition for Accuracy-first Mechanisms
9. NeurIPS 2023Adversarially Robust Distributed Count Tracking via Partial Differential Privacy
10. NeurIPS 2023An Optimal and Scalable Matrix Mechanism for Noisy Marginals under Convex Loss Functions
11. NeurIPS 2023Better Private Linear Regression Through Better Private Feature Selection
12. NeurIPS 2023Black-Box Differential Privacy for Interactive ML
13. NeurIPS 2023Bounding training data reconstruction in DP-SGD
14. NeurIPS 2023Breaking the Communication-Privacy-Accuracy Tradeoff with $f$-Differential Privacy
15. NeurIPS 2023Counting Distinct Elements in the Turnstile Model with Differential Privacy under Continual Observation
16. NeurIPS 2023Counting Distinct Elements Under Person-Level Differential Privacy
17. NeurIPS 2023Creating a Public Repository for Joining Private Data
18. NeurIPS 2023Decision Tree for Locally Private Estimation with Public Data
19. NeurIPS 2023Differentially Private Approximate Near Neighbor Counting in High Dimensions
20. NeurIPS 2023Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protection
21. NeurIPS 2023Differentially Private Statistical Inference through $\beta$-Divergence One Posterior Sampling
22. NeurIPS 2023DP-HyPO: An Adaptive Private Framework for Hyperparameter Optimization
23. NeurIPS 2023DP-Mix: Mixup-based Data Augmentation for Differentially Private Learning
24. NeurIPS 2023Dynamic Personalized Federated Learning with Adaptive Differential Privacy
25. NeurIPS 2023Efficient Sampling of Stochastic Differential Equations with Positive Semi-Definite Models
26. NeurIPS 2023Exact Optimality of Communication-Privacy-Utility Tradeoffs in Distributed Mean Estimation
27. NeurIPS 2023Fast Optimal Locally Private Mean Estimation via Random Projections
28. NeurIPS 2023Faster approximate subgraph counts with privacy
29. NeurIPS 2023Faster Differentially Private Convex Optimization via Second-Order Methods
30. NeurIPS 2023Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models
31. NeurIPS 2023Functional Renyi Differential Privacy for Generative Modeling
32. NeurIPS 2023Gaussian Differential Privacy on Riemannian Manifolds
33. NeurIPS 2023Generalization in the Face of Adaptivity: A Bayesian Perspective
34. NeurIPS 2023Have it your way: Individualized Privacy Assignment for DP-SGD
35. NeurIPS 2023Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners
36. NeurIPS 2023k-Median Clustering via Metric Embedding: Towards Better Initialization with Differential Privacy
37. NeurIPS 2023Label Robust and Differentially Private Linear Regression: Computational and Statistical Efficiency
38. NeurIPS 2023Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack
39. NeurIPS 2023Minimax Risks and Optimal Procedures for Estimation under Functional Local Differential Privacy
40. NeurIPS 2023Nearly Tight Bounds For Differentially Private Multiway Cut
41. NeurIPS 2023Neural Fields with Hard Constraints of Arbitrary Differential Order
42. NeurIPS 2023Neural Graph Generation from Graph Statistics
43. NeurIPS 2023Offline Reinforcement Learning with Differential Privacy
44. NeurIPS 2023On Computing Pairwise Statistics with Local Differential Privacy
45. NeurIPS 2023On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence
46. NeurIPS 2023On the Gini-impurity Preservation For Privacy Random Forests
47. NeurIPS 2023Optimal privacy guarantees for a relaxed threat model: Addressing sub-optimal adversaries in differentially private machine learning
48. NeurIPS 2023Optimal Unbiased Randomizers for Regression with Label Differential Privacy
49. NeurIPS 2023Post-processing Private Synthetic Data for Improving Utility on Selected Measures
50. NeurIPS 2023Practical Differentially Private Hyperparameter Tuning with Subsampling

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。