Differential Privacy papers, 2023–2026

Key findings

• Differential Privacy fell from 117 papers in 2023 to 103 in 2026, so interest is cooling.
• NeurIPS publishes the most Differential Privacy work: 217 papers from 2023 to 2026, 45% of the four-venue total.
• The fastest-growing overlap is with Social aspects · accountability transparency and interpretability: papers tagged with both rose from 0 in 2023 to 22 in 2026.
• Among the 5 topics under Federated and Privacy, it ranks #3 by 2026 paper count; the fastest grower in the group, Secure Aggregation, is up 1.8x versus 0.9x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Differential Privacy papers

103 papers, page 1 of 3

1. CVPR 2026DiG Differential Grounding for Enhancing Fine-Grained Perception in Multimodal Large
2. CVPR 2026Fully Decentralized Certified Unlearning
3. CVPR 2026LDP-Slicing Local Differential Privacy for Images via Randomized Bit-Plane Slicing
4. CVPR 2026Personalized Federated Training of Diffusion Models with Privacy Guarantees
5. CVPR 2026SpiderCam Low-Power Snapshot Depth from Differential Defocus
6. CVPR 2026Taming Noise-Induced Prototype Degradation for Privacy-Preserving Personalized Federated Fine-Tuning
7. CVPR 2026Towards Cross-Modal Preservation Consistency and Alignment for Privacy-Preserving Visible-Infrared Person
8. ICLR 2026Adaptive Methods Are Preferable in High Privacy Settings: An SDE Perspective
9. ICLR 2026Back to Square Roots: An Optimal Bound on the Matrix Factorization Error for Multi-Epoch Differentially Private SGD
10. ICLR 2026Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models
11. ICLR 2026Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy
12. ICLR 2026Convergent Differential Privacy Analysis for General Federated Learning
13. ICLR 2026Differentially Private Domain Discovery
14. ICLR 2026Differentially Private Equilibrium Finding in Polymatrix Games
15. ICLR 2026Differentially Private Two-Stage Gradient Descent for Instrumental Variable Regression
16. ICLR 2026Disentangled Representation Learning for Parametric Partial Differential Equations
17. ICLR 2026DPQuant: Efficient and Private Model Training via Dynamic Quantization Scheduling
18. ICLR 2026Exponential-Wrapped Mechanisms: Differential Privacy on Hadamard Manifolds Made Practical
19. ICLR 2026Federated Learning of Quantile Inference under Local Differential Privacy
20. ICLR 2026Hot PATE: Private Aggregation of Distributions for Diverse Tasks
21. ICLR 2026INO-SGD: Addressing Utility Imbalance under Individualized Differential Privacy
22. ICLR 2026Label Smoothing Improves Machine Unlearning
23. ICLR 2026Mean-Field Neural Differential Equations: A Game-Theoretic Approach to Sequence Prediction
24. ICLR 2026Mitigating Privacy Risk via Forget Set-Free Unlearning
25. ICLR 2026Natural Identifiers for Privacy and Data Audits in Large Language Models
26. ICLR 2026On Optimal Hyperparameters for Differentially Private Deep Transfer Learning
27. ICLR 2026On the trade-off between expressivity and privacy in graph representation learning
28. ICLR 2026Optimizing Canaries for Privacy Auditing with Metagradient Descent
29. ICLR 2026PE-SGD: Differentially Private Deep Learning via Evolution of Gradient Subspace for Text
30. ICLR 2026PetaGAIL++: Utility Optimized Private Trajectory Generation with Imitation Learning
31. ICLR 2026Prediction with Expert Advice under Local Differential Privacy
32. ICLR 2026Predictive Differential Training Guided by Training Dynamics
33. ICLR 2026Random Controlled Differential Equations
34. ICLR 2026Rethinking LoRA for Privacy-Preserving Federated Learning in Large Models
35. ICLR 2026Riesz Neural Operator for Solving Partial Differential Equations
36. ICLR 2026Skirting Additive Error Lower Bounds for Private Turnstile Streams
37. ICLR 2026Understanding Sensitivity of Differential Attention through the Lens of Adversarial Robustness
38. ICLR 2026Unified Privacy Guarantees for Decentralized Learning via Matrix Factorization
39. ICML 2026Accuracy-First Rényi Differential Privacy and Post-Processing Immunity
40. ICML 2026Accurate, Private, Secure, Federated U-statistics with Higher Degree
41. ICML 2026Barriers to Counterfactual Credit Attribution for Autoregressive Models
42. ICML 2026Censoring with Plausible Deniability: Asymmetric Local Privacy for Multi-Category CDF Estimation
43. ICML 2026Content-Style Identification via Differential Independence
44. ICML 2026Decoupling Regularization and Privacy in Differentially Private Ridge Regression and ERM
45. ICML 2026Differentially Private Continual Release with Relative Error
46. ICML 2026Differentially Private Cross-Silo Recommendation from Implicit Feedback
47. ICML 2026Differentially Private Geodesic Regression
48. ICML 2026Differentially Private Preference Data Synthesis for Large Language Model Alignment
49. ICML 2026Differentially Private Range Subgraph Counting
50. ICML 2026Differentially Private Submodular Maximization with a Knapsack Constraint

FAQ

How many Differential Privacy papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

479 in total: 117 in 2023, 113 in 2024, 146 in 2025, 103 in 2026.

How many Differential Privacy papers are at NeurIPS 2026?

NeurIPS 2026 has 23 Differential Privacy papers, versus 66 the year before.

How many Differential Privacy papers are at ICLR 2026?

ICLR 2026 has 31 Differential Privacy papers, versus 29 the year before.

How many Differential Privacy papers are at ICML 2026?

ICML 2026 has 42 Differential Privacy papers, versus 47 the year before.

How many Differential Privacy papers are at CVPR 2026?

CVPR 2026 has 7 Differential Privacy papers, versus 4 the year before.

Which conference publishes the most Differential Privacy papers?

NeurIPS, with 217 papers from 2023 to 2026.