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 29 篇，第 1 / 1 页

1. ICLR 2025Adaptive Batch Size for Privately Finding Second-Order Stationary Points
2. ICLR 2025Adaptive Pruning of Pretrained Transformer via Differential Inclusions
3. ICLR 2025Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness
4. ICLR 2025Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning
5. ICLR 2025Differential Transformer
6. ICLR 2025Differentially Private Federated Learning with Time-Adaptive Privacy Spending
7. ICLR 2025Differentially private learners for heterogeneous treatment effects
8. ICLR 2025Differentially private optimization for non-decomposable objective functions
9. ICLR 2025Differentially Private Steering for Large Language Model Alignment
10. ICLR 2025DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction
11. ICLR 2025Enhancing Learning with Label Differential Privacy by Vector Approximation
12. ICLR 2025Gaussian Differentially Private Human Faces Under a Face Radial Curve Representation
13. ICLR 2025Learning from End User Data with Shuffled Differential Privacy over Kernel Densities
14. ICLR 2025Learning vector fields of differential equations on manifolds with geometrically constrained operator-valued kernels
15. ICLR 2025Local convergence of simultaneous min-max algorithms to differential equilibrium on Riemannian manifold
16. ICLR 2025Near-Exact Privacy Amplification for Matrix Mechanisms
17. ICLR 2025On the Price of Differential Privacy for Hierarchical Clustering
18. ICLR 2025Optimality of Matrix Mechanism on $\ell_p^p$-metric
19. ICLR 2025PFGuard: A Generative Framework with Privacy and Fairness Safeguards
20. ICLR 2025Privacy Auditing of Large Language Models
21. ICLR 2025Privacy-Preserving Personalized Federated Prompt Learning for Multimodal Large Language Models
22. ICLR 2025Private Mechanism Design via Quantile Estimation
23. ICLR 2025Privately Counting Partially Ordered Data
24. ICLR 2025Scaling up the Banded Matrix Factorization Mechanism for Large Scale Differentially Private ML
25. ICLR 2025Singular Subspace Perturbation Bounds via Rectangular Random Matrix Diffusions
26. ICLR 2025The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
27. ICLR 2025The Utility and Complexity of In- and Out-of-Distribution Machine Unlearning
28. ICLR 2025Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
29. ICLR 2025Towards hyperparameter-free optimization with differential privacy

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。