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 106 篇，第 2 / 3 页

51. ICLR 2025Privacy Auditing of Large Language Models
52. ICLR 2025Privacy-Preserving Personalized Federated Prompt Learning for Multimodal Large Language Models
53. ICLR 2025Private Mechanism Design via Quantile Estimation
54. ICLR 2025Privately Counting Partially Ordered Data
55. ICLR 2025Scaling up the Banded Matrix Factorization Mechanism for Large Scale Differentially Private ML
56. ICLR 2025Singular Subspace Perturbation Bounds via Rectangular Random Matrix Diffusions
57. ICLR 2025The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
58. ICLR 2025The Utility and Complexity of In- and Out-of-Distribution Machine Unlearning
59. ICLR 2025Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
60. ICLR 2025Towards hyperparameter-free optimization with differential privacy
61. ICLR 2024A Differentially Private Clustering Algorithm for Well-Clustered Graphs
62. ICLR 2024Decoupled Marked Temporal Point Process using Neural Ordinary Differential Equations
63. ICLR 2024Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
64. ICLR 2024Differentially Private Synthetic Data via Foundation Model APIs 1: Images
65. ICLR 2024DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
66. ICLR 2024Efficiently Computing Similarities to Private Datasets
67. ICLR 2024FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity
68. ICLR 2024Fixed-Budget Differentially Private Best Arm Identification
69. ICLR 2024Improved Analysis of Sparse Linear Regression in Local Differential Privacy Model
70. ICLR 2024Improving LoRA in Privacy-preserving Federated Learning
71. ICLR 2024LabelDP-Pro: Learning with Label Differential Privacy via Projections
72. ICLR 2024Learning No-Regret Sparse Generalized Linear Models with Varying Observation(s)
73. ICLR 2024Neural structure learning with stochastic differential equations
74. ICLR 2024On Differentially Private Federated Linear Contextual Bandits
75. ICLR 2024One-shot Empirical Privacy Estimation for Federated Learning
76. ICLR 2024Privacy Amplification for Matrix Mechanisms
77. ICLR 2024Privacy-Preserving In-Context Learning for Large Language Models
78. ICLR 2024Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
79. ICLR 2024Private Zeroth-Order Nonsmooth Nonconvex Optimization
80. ICLR 2024Privately Aligning Language Models with Reinforcement Learning
81. ICLR 2024SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations
82. ICLR 2024Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data
83. ICLR 2024Tangent Transformers for Composition,Privacy and Removal
84. ICLR 2024The importance of feature preprocessing for differentially private linear optimization
85. ICLR 2024Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy
86. ICLR 2023A Statistical Framework for Personalized Federated Learning and Estimation: Theory, Algorithms, and Privacy
87. ICLR 2023Anamnesic Neural Differential Equations with Orthogonal Polynomial Projections
88. ICLR 2023CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning
89. ICLR 2023Characteristic Neural Ordinary Differential Equation
90. ICLR 2023Coupled Multiwavelet Operator Learning for Coupled Differential Equations
91. ICLR 2023Differentially Private $L_2$-Heavy Hitters in the Sliding Window Model
92. ICLR 2023Differentially Private Adaptive Optimization with Delayed Preconditioners
93. ICLR 2023Disparate Impact in Differential Privacy from Gradient Misalignment
94. ICLR 2023Distributed Differential Privacy in Multi-Armed Bandits
95. ICLR 2023Easy Differentially Private Linear Regression
96. ICLR 2023Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping
97. ICLR 2023Improved Convergence of Differential Private SGD with Gradient Clipping
98. ICLR 2023Individual Privacy Accounting with Gaussian Differential Privacy
99. ICLR 2023Neural ePDOs: Spatially Adaptive Equivariant Partial Differential Operator Based Networks
100. ICLR 2023Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses

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。