差分隐私论文趋势 2023–2026
DP 训练
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 479 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 67 | 21 | 27 | 2 | 117 |
| 2024 | 61 | 25 | 24 | 3 | 113 |
| 2025 | 66 | 29 | 47 | 4 | 146 |
| 2026 | 23 | 31 | 42 | 7 | 103 |
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 6 / 10 页
- CVPR 2024All Rivers Run to the Sea: Private Learning with Asymmetric Flows
- CVPR 2024Privacy-Preserving Optics for Enhancing Protection in Face De-Identification
- ICLR 2024A Differentially Private Clustering Algorithm for Well-Clustered Graphs
- ICLR 2024Decoupled Marked Temporal Point Process using Neural Ordinary Differential Equations
- ICLR 2024Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
- ICLR 2024Differentially Private Synthetic Data via Foundation Model APIs 1: Images
- ICLR 2024DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
- ICLR 2024Efficiently Computing Similarities to Private Datasets
- ICLR 2024FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity
- ICLR 2024Fixed-Budget Differentially Private Best Arm Identification
- ICLR 2024Improved Analysis of Sparse Linear Regression in Local Differential Privacy Model
- ICLR 2024Improving LoRA in Privacy-preserving Federated Learning
- ICLR 2024LabelDP-Pro: Learning with Label Differential Privacy via Projections
- ICLR 2024Learning No-Regret Sparse Generalized Linear Models with Varying Observation(s)
- ICLR 2024Neural structure learning with stochastic differential equations
- ICLR 2024On Differentially Private Federated Linear Contextual Bandits
- ICLR 2024One-shot Empirical Privacy Estimation for Federated Learning
- ICLR 2024Privacy Amplification for Matrix Mechanisms
- ICLR 2024Privacy-Preserving In-Context Learning for Large Language Models
- ICLR 2024Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
- ICLR 2024Private Zeroth-Order Nonsmooth Nonconvex Optimization
- ICLR 2024Privately Aligning Language Models with Reinforcement Learning
- ICLR 2024SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations
- ICLR 2024Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data
- ICLR 2024Tangent Transformers for Composition,Privacy and Removal
- ICLR 2024The importance of feature preprocessing for differentially private linear optimization
- ICLR 2024Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy
- ICML 2024Auditing Private Prediction
- ICML 2024Beyond the Calibration Point: Mechanism Comparison in Differential Privacy
- ICML 2024Delving into Differentially Private Transformer
- ICML 2024Diffusion Tempering Improves Parameter Estimation with Probabilistic Integrators for Ordinary Differential Equations
- ICML 2024Hyperbolic Optimizer as a Dynamical System
- ICML 2024Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy
- ICML 2024Log Neural Controlled Differential Equations: The Lie Brackets Make A Difference
- ICML 2024Mean Estimation in the Add-Remove Model of Differential Privacy
- ICML 2024Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss
- ICML 2024Neural Collapse meets Differential Privacy: Curious behaviors of NoisyGD with Near-Perfect Representation Learning
- ICML 2024Optimal Differentially Private Model Training with Public Data
- ICML 2024Privacy Backdoors: Stealing Data with Corrupted Pretrained Models
- ICML 2024Privacy Profiles for Private Selection
- ICML 2024Privacy-Preserving Instructions for Aligning Large Language Models
- ICML 2024Privately Learning Smooth Distributions on the Hypercube by Projections
- ICML 2024Provable Privacy with Non-Private Pre-Processing
- ICML 2024Shifted Interpolation for Differential Privacy
- ICML 2024Split-and-Denoise: Protect large language model inference with local differential privacy
- ICML 2024Stability-Informed Initialization of Neural Ordinary Differential Equations
- ICML 2024Stabilizing Policy Gradients for Stochastic Differential Equations via Consistency with Perturbation Process
- ICML 2024State-Constrained Zero-Sum Differential Games with One-Sided Information
- ICML 2024The Privacy Power of Correlated Noise in Decentralized Learning
- ICML 2024Tuning-free Estimation and Inference of Cumulative Distribution Function under Local Differential Privacy
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查差分隐私在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "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。