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 479 篇，第 3 / 10 页

101. NeurIPS 2026Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits
102. NeurIPS 2026Sort, Partition, Randomize: Optimal Binary Hypothesis Testing under Local Differential Privacy
103. NeurIPS 2026The Price of Locality in Label Privacy: Optimal Rates for Classification and Regression
104. CVPR 2025Accurate Differential Operators for Hybrid Neural Fields
105. CVPR 2025Explicit Depth-Aware Blurry Video Frame Interpolation Guided by Differential Curves
106. CVPR 2025Focal Split: Untethered Snapshot Depth from Differential Defocus
107. CVPR 2025Unveiling Differences in Generative Models: A Scalable Differential Clustering Approach
108. ICLR 2025Adaptive Batch Size for Privately Finding Second-Order Stationary Points
109. ICLR 2025Adaptive Pruning of Pretrained Transformer via Differential Inclusions
110. ICLR 2025Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness
111. ICLR 2025Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning
112. ICLR 2025Differential Transformer
113. ICLR 2025Differentially Private Federated Learning with Time-Adaptive Privacy Spending
114. ICLR 2025Differentially private learners for heterogeneous treatment effects
115. ICLR 2025Differentially private optimization for non-decomposable objective functions
116. ICLR 2025Differentially Private Steering for Large Language Model Alignment
117. ICLR 2025DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction
118. ICLR 2025Enhancing Learning with Label Differential Privacy by Vector Approximation
119. ICLR 2025Gaussian Differentially Private Human Faces Under a Face Radial Curve Representation
120. ICLR 2025Learning from End User Data with Shuffled Differential Privacy over Kernel Densities
121. ICLR 2025Learning vector fields of differential equations on manifolds with geometrically constrained operator-valued kernels
122. ICLR 2025Local convergence of simultaneous min-max algorithms to differential equilibrium on Riemannian manifold
123. ICLR 2025Near-Exact Privacy Amplification for Matrix Mechanisms
124. ICLR 2025On the Price of Differential Privacy for Hierarchical Clustering
125. ICLR 2025Optimality of Matrix Mechanism on $\ell_p^p$-metric
126. ICLR 2025PFGuard: A Generative Framework with Privacy and Fairness Safeguards
127. ICLR 2025Privacy Auditing of Large Language Models
128. ICLR 2025Privacy-Preserving Personalized Federated Prompt Learning for Multimodal Large Language Models
129. ICLR 2025Private Mechanism Design via Quantile Estimation
130. ICLR 2025Privately Counting Partially Ordered Data
131. ICLR 2025Scaling up the Banded Matrix Factorization Mechanism for Large Scale Differentially Private ML
132. ICLR 2025Singular Subspace Perturbation Bounds via Rectangular Random Matrix Diffusions
133. ICLR 2025The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
134. ICLR 2025The Utility and Complexity of In- and Out-of-Distribution Machine Unlearning
135. ICLR 2025Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
136. ICLR 2025Towards hyperparameter-free optimization with differential privacy
137. ICML 2025Adapting to Linear Separable Subsets with Large-Margin in Differentially Private Learning
138. ICML 2025Approximate Differential Privacy of the $\ell_2$ Mechanism
139. ICML 2025Auditing $f$-differential privacy in one run
140. ICML 2025Breaking the $n^{1.5}$ Additive Error Barrier for Private and Efficient Graph Sparsification via Private Expander Decomposition
141. ICML 2025Breaking the Quadratic Barrier: Robust Cardinality Sketches for Adaptive Queries
142. ICML 2025Cape: Context-Aware Prompt Perturbation Mechanism with Differential Privacy
143. ICML 2025Certification for Differentially Private Prediction in Gradient-Based Training
144. ICML 2025Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off
145. ICML 2025Differential Coding for Training-Free ANN-to-SNN Conversion
146. ICML 2025Differential Privacy Guarantees of Markov Chain Monte Carlo Algorithms
147. ICML 2025Differential Privacy Under Class Imbalance: Methods and Empirical Insights
148. ICML 2025Differentially Private Analysis for Binary Response Models: Optimality, Estimation, and Inference
149. ICML 2025Differentially Private Boxplots
150. ICML 2025Differentially Private Federated $k$-Means Clustering with Server-Side 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。