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 140 篇，第 3 / 3 页

101. ICML 2024Privacy Backdoors: Stealing Data with Corrupted Pretrained Models
102. ICML 2024Privacy Profiles for Private Selection
103. ICML 2024Privacy-Preserving Instructions for Aligning Large Language Models
104. ICML 2024Privately Learning Smooth Distributions on the Hypercube by Projections
105. ICML 2024Provable Privacy with Non-Private Pre-Processing
106. ICML 2024Shifted Interpolation for Differential Privacy
107. ICML 2024Split-and-Denoise: Protect large language model inference with local differential privacy
108. ICML 2024Stability-Informed Initialization of Neural Ordinary Differential Equations
109. ICML 2024Stabilizing Policy Gradients for Stochastic Differential Equations via Consistency with Perturbation Process
110. ICML 2024State-Constrained Zero-Sum Differential Games with One-Sided Information
111. ICML 2024The Privacy Power of Correlated Noise in Decentralized Learning
112. ICML 2024Tuning-free Estimation and Inference of Cumulative Distribution Function under Local Differential Privacy
113. ICML 2024Unveiling Privacy, Memorization, and Input Curvature Links
114. ICML 2023A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining
115. ICML 2023Algorithms for bounding contribution for histogram estimation under user-level privacy
116. ICML 2023Bayesian Estimation of Differential Privacy
117. ICML 2023Concurrent Shuffle Differential Privacy Under Continual Observation
118. ICML 2023Controlled Differential Equations on Long Sequences via Non-standard Wavelets
119. ICML 2023DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learning
120. ICML 2023Differential Privacy has Bounded Impact on Fairness in Classification
121. ICML 2023Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models
122. ICML 2023Differentially Private Sharpness-Aware Training
123. ICML 2023Effectively Using Public Data in Privacy Preserving Machine Learning
124. ICML 2023Federated Linear Contextual Bandits with User-level Differential Privacy
125. ICML 2023Fully-Adaptive Composition in Differential Privacy
126. ICML 2023Group Equivariant Fourier Neural Operators for Partial Differential Equations
127. ICML 2023Image Restoration with Mean-Reverting Stochastic Differential Equations
128. ICML 2023Label differential privacy and private training data release
129. ICML 2023Locally Regularized Neural Differential Equations: Some Black Boxes were meant to remain closed!
130. ICML 2023Multi-Task Differential Privacy Under Distribution Skew
131. ICML 2023Neural Stochastic Differential Games for Time-series Analysis
132. ICML 2023Online Local Differential Private Quantile Inference via Self-normalization
133. ICML 2023Predicting Ordinary Differential Equations with Transformers
134. ICML 2023Private Statistical Estimation of Many Quantiles
135. ICML 2023Random Grid Neural Processes for Parametric Partial Differential Equations
136. ICML 2023Sketching Meets Differential Privacy: Fast Algorithm for Dynamic Kronecker Projection Maintenance
137. ICML 2023Statistical Indistinguishability of Learning Algorithms
138. ICML 2023Streaming Submodular Maximization with Differential Privacy
139. ICML 2023The Price of Differential Privacy under Continual Observation
140. ICML 2023The Saddle-Point Method in 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。