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 113 篇，第 2 / 3 页

51. ICML 2024Tuning-free Estimation and Inference of Cumulative Distribution Function under Local Differential Privacy
52. ICML 2024Unveiling Privacy, Memorization, and Input Curvature Links
53. NeurIPS 2024$\texttt{pfl-research}$: simulation framework for accelerating research in Private Federated Learning
54. NeurIPS 2024A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy
55. NeurIPS 2024Advection Augmented Convolutional Neural Networks
56. NeurIPS 2024Adversarially Robust Dense-Sparse Tradeoffs via Heavy-Hitters
57. NeurIPS 2024An Efficient High-dimensional Gradient Estimator for Stochastic Differential Equations
58. NeurIPS 2024Attack-Aware Noise Calibration for Differential Privacy
59. NeurIPS 2024Auditing Privacy Mechanisms via Label Inference Attacks
60. NeurIPS 2024Banded Square Root Matrix Factorization for Differentially Private Model Training
61. NeurIPS 2024Certified Machine Unlearning via Noisy Stochastic Gradient Descent
62. NeurIPS 2024Continual Counting with Gradual Privacy Expiration
63. NeurIPS 2024Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature
64. NeurIPS 2024Differential Privacy in Scalable General Kernel Learning via $K$-means Nystr{\"o}m Random Features
65. NeurIPS 2024Differentially Private Graph Diffusion with Applications in Personalized PageRanks
66. NeurIPS 2024Differentially Private Optimization with Sparse Gradients
67. NeurIPS 2024Differentially Private Set Representations
68. NeurIPS 2024Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement
69. NeurIPS 2024Dimension-free Private Mean Estimation for Anisotropic Distributions
70. NeurIPS 2024DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction
71. NeurIPS 2024Efficient and Private Marginal Reconstruction with Local Non-Negativity
72. NeurIPS 2024Exactly Minimax-Optimal Locally Differentially Private Sampling
73. NeurIPS 2024Faster Algorithms for User-Level Private Stochastic Convex Optimization
74. NeurIPS 2024Faster Differentially Private Top-$k$ Selection: A Joint Exponential Mechanism with Pruning
75. NeurIPS 2024Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups
76. NeurIPS 2024Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Data
77. NeurIPS 2024From Biased to Unbiased Dynamics: An Infinitesimal Generator Approach
78. NeurIPS 2024HEPrune: Fast Private Training of Deep Neural Networks With Encrypted Data Pruning
79. NeurIPS 2024Improving Neural Network Surface Processing with Principal Curvatures
80. NeurIPS 2024Instance-Optimal Private Density Estimation in the Wasserstein Distance
81. NeurIPS 2024Instance-Specific Asymmetric Sensitivity in Differential Privacy
82. NeurIPS 2024Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
83. NeurIPS 2024Locally Private and Robust Multi-Armed Bandits
84. NeurIPS 2024Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
85. NeurIPS 2024Noisy Dual Mirror Descent: A Near Optimal Algorithm for Jointly-DP Convex Resource Allocation
86. NeurIPS 2024On Differentially Private Subspace Estimation in a Distribution-Free Setting
87. NeurIPS 2024On Differentially Private U Statistics
88. NeurIPS 2024On the Computational Complexity of Private High-dimensional Model Selection
89. NeurIPS 2024Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives
90. NeurIPS 2024Optimal Private and Communication Constraint Distributed Goodness-of-Fit Testing for Discrete Distributions in the Large Sample Regime
91. NeurIPS 2024Oracle-Efficient Differentially Private Learning with Public Data
92. NeurIPS 2024PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
93. NeurIPS 2024Pre-training Differentially Private Models with Limited Public Data
94. NeurIPS 2024Prior-itizing Privacy: A Bayesian Approach to Setting the Privacy Budget in Differential Privacy
95. NeurIPS 2024Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training
96. NeurIPS 2024Private Algorithms for Stochastic Saddle Points and Variational Inequalities: Beyond Euclidean Geometry
97. NeurIPS 2024Private Edge Density Estimation for Random Graphs: Optimal, Efficient and Robust
98. NeurIPS 2024Private Geometric Median
99. NeurIPS 2024Private Online Learning via Lazy Algorithms
100. NeurIPS 2024Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions

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。