社会层面 · privacy论文趋势 2023–2026

主要结论

• 社会层面 · privacy论文从 2023 年的 21 篇增长到 2026 年的 138 篇，三年间扩大到约 6.6 倍。
• NeurIPS 是发社会层面 · privacy论文最多的会议，2023–2026 年共 215 篇，占四个会议总量的 50%。
• 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 93 篇。
• 在「对齐与负责任 AI」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的社会层面 · safety是 93 倍，社会层面 · privacy是 6.6 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 2026Assessing Per-Sample Membership Inference Vulnerability without Retraining
• ICML 2026Accuracy-First Rényi Differential Privacy and Post-Processing Immunity
• ICLR 2026Mitigating Privacy Risk via Forget Set-Free Unlearning
• CVPR 2026Protego User-Centric Pose-Invariant Privacy Protection Against Face Recognition-Induced Digital Footprint
• NeurIPS 2025A Generalized Binary Tree Mechanism for Private Approximation of All-Pair Shortest Distances
• ICML 2025Breaking the $n^{1.5}$ Additive Error Barrier for Private and Efficient Graph Sparsification via Private Expander Decomposition
• ICLR 2025Machine Unlearning via Simulated Oracle Matching
• CVPR 2025Enhancing Facial Privacy Protection via Weakening Diffusion Purification
• NeurIPS 2024Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
• ICML 2024Privacy Preserving Adaptive Experiment Design
• ICLR 2024Beyond Memorization: Violating Privacy via Inference with Large Language Models
• CVPR 2024Validating Privacy-Preserving Face Recognition under a Minimum Assumption
• NeurIPS 2023Faster approximate subgraph counts with privacy
• ICML 2023GuardHFL: Privacy Guardian for Heterogeneous Federated Learning
• ICLR 2023Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models
• CVPR 2023Privacy-Preserving Representations Are Not Enough: Recovering Scene Content From Camera Poses
• NeurIPS 2026Asymmetric Invertible Threat: Learning Reversible Privacy Defense for Face Recognition
• ICML 2026Accurate, Private, Secure, Federated U-statistics with Higher Degree
• ICLR 2026Measuring Physical-World Privacy Awareness of Large Language Models: An Evaluation Benchmark
• CVPR 2026LDP-Slicing Local Differential Privacy for Images via Randomized Bit-Plane Slicing

全部社会层面 · privacy论文

共 431 篇，第 1 / 9 页

1. CVPR 2026LDP-Slicing Local Differential Privacy for Images via Randomized Bit-Plane Slicing
2. CVPR 2026Protego User-Centric Pose-Invariant Privacy Protection Against Face Recognition-Induced Digital Footprint
3. ICLR 2026Measuring Physical-World Privacy Awareness of Large Language Models: An Evaluation Benchmark
4. ICLR 2026Mitigating Privacy Risk via Forget Set-Free Unlearning
5. ICML 2026*MemPot*: Defend Against Memory Extraction Attack with Optimized Honeypots
6. ICML 2026$\texttt{FHAIM}$: Fully Homomorphic AIM for Private Tabular Synthetic Data Generation
7. ICML 2026Accuracy-First Rényi Differential Privacy and Post-Processing Immunity
8. ICML 2026Accurate, Private, Secure, Federated U-statistics with Higher Degree
9. ICML 2026ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted Control
10. ICML 2026Adaptively Robust Resettable Streaming
11. ICML 2026An Empirical Study on the Resilience of Partial Merging to Model Clone Attacks
12. ICML 2026ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models
13. ICML 2026Asymptotic Optimality of the High-Dimensional Gaussian Mechanism and Improved Low-Dimensional Mechanisms for Differential Privacy
14. ICML 2026Beyond Sample-Level Forgetting: Improving Reliability in Multimodal Unlearning
15. ICML 2026Censoring with Plausible Deniability: Asymmetric Local Privacy for Multi-Category CDF Estimation
16. ICML 2026Continual Learning With Participation Privacy: An Auditable Buffering-Aggregation Recipe
17. ICML 2026Decoupling Regularization and Privacy in Differentially Private Ridge Regression and ERM
18. ICML 2026Differentially Private Continual Release with Relative Error
19. ICML 2026Differentially Private Cross-Silo Recommendation from Implicit Feedback
20. ICML 2026Differentially Private Geodesic Regression
21. ICML 2026Differentially Private Preference Data Synthesis for Large Language Model Alignment
22. ICML 2026Differentially Private Range Subgraph Counting
23. ICML 2026Differentially Private Submodular Maximization with a Knapsack Constraint
24. ICML 2026Differentially Private Synthetic Data via APIs 4: Tabular Data
25. ICML 2026DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning
26. ICML 2026Efficient DP-SGD for LLMs with Randomized Clipping
27. ICML 2026Efficient privacy loss accounting for subsampling and random allocation
28. ICML 2026Efficient Public Verification of Private ML via Regularization
29. ICML 2026Eliminating Solution Bias in Differentially Private Optimization
30. ICML 2026Enhancing Membership Inference Attacks on Diffusion Models from a Frequency-Domain Perspective
31. ICML 2026EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors
32. ICML 2026Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs
33. ICML 2026Exploring Nonlinear Pathway in Parameter Space for Machine Unlearning
34. ICML 2026Fast and Near-Optimal Algorithms for Private Hypothesis Selection
35. ICML 2026Federated Manifold Learning (FML): Tackling Domain Heterogeneity with Structural Knowledge Transfer
36. ICML 2026Finding Differentially Private Second Order Stationary Points in Stochastic Minimax Optimization
37. ICML 2026Finding DoRI: Discovery of Retained Images in Diffusion Models
38. ICML 2026FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space
39. ICML 2026Forget to Know, Remember to Use: Context-Aware Unlearning for Large Language Models
40. ICML 2026From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
41. ICML 2026From Weak Cues to Real Identities: Evaluating Inference-Driven De-Anonymization in LLM Agents
42. ICML 2026FUSE: Full‑spectrum Unlearnable Examples via Spectral Equalization
43. ICML 2026FuseFSS: Efficient Secure LLM Inference with Function Secret Sharing
44. ICML 2026Gradient Inversion Attacks Beyond SGD
45. ICML 2026Heterogeneity-Aware Knowledge Sharing for Graph Federated Learning
46. ICML 2026Homophily-Heterogeneity Gradient Surgery for Federated Graph Learning
47. ICML 2026How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning
48. ICML 2026Improved Bounds for Private and Robust Alignment
49. ICML 2026Keeping a Secret Requires a Good Memory: Unconditional Streaming Lower-Bounds for Differentially Private Algorithms
50. ICML 2026LAPRAS : Learning-Augmented PRivate Answering for linear query Streams.

常见问题

2023–2026 年四大会议一共有多少篇社会层面 · privacy论文？

共 431 篇，按年份分别是 2023 年 21 篇、2024 年 117 篇、2025 年 155 篇、2026 年 138 篇。

NeurIPS 2026 有多少篇社会层面 · privacy论文？

NeurIPS 2026 有 44 篇社会层面 · privacy论文，上一届是 80 篇。

ICLR 2026 有多少篇社会层面 · privacy论文？

ICLR 2026 有 2 篇社会层面 · privacy论文，上一届是 2 篇。

ICML 2026 有多少篇社会层面 · privacy论文？

ICML 2026 有 90 篇社会层面 · privacy论文，上一届是 71 篇。

CVPR 2026 有多少篇社会层面 · privacy论文？

CVPR 2026 有 2 篇社会层面 · privacy论文，上一届是 2 篇。

哪个会议的社会层面 · privacy论文最多？

NeurIPS，2023–2026 年共 215 篇。