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 80 篇，第 2 / 2 页

51. NeurIPS 2025Private Continual Counting of Unbounded Streams
52. NeurIPS 2025Private Geometric Median in Nearly-Linear Time
53. NeurIPS 2025Private Hyperparameter Tuning with Ex-Post Guarantee
54. NeurIPS 2025Private Set Union with Multiple Contributions
55. NeurIPS 2025Private Zeroth-Order Optimization with Public Data
56. NeurIPS 2025Probabilistic Reasoning with LLMs for Privacy Risk Estimation
57. NeurIPS 2025Purifying Approximate Differential Privacy with Randomized Post-processing
58. NeurIPS 2025Query-Efficient Locally Private Hypothesis Selection via the Scheffe Graph
59. NeurIPS 2025Rethinking Fair Federated Learning from Parameter and Client View
60. NeurIPS 2025Rethinking the Role of Verbatim Memorization in LLM Privacy
61. NeurIPS 2025Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions
62. NeurIPS 2025RUAGO: Effective and Practical Retain-Free Unlearning via Adversarial Attack and OOD Generator
63. NeurIPS 2025Second-Order Convergence in Private Stochastic Non-Convex Optimization
64. NeurIPS 2025Secure and Confidential Certificates of Online Fairness
65. NeurIPS 2025Sequentially Auditing Differential Privacy
66. NeurIPS 2025Setting $\varepsilon$ is not the Issue in Differential Privacy
67. NeurIPS 2025Sketched Gaussian Mechanism for Private Federated Learning
68. NeurIPS 2025Subgraph Federated Learning via Spectral Methods
69. NeurIPS 2025Sum Estimation under Personalized Local Differential Privacy
70. NeurIPS 2025Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries
71. NeurIPS 2025The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples
72. NeurIPS 2025Time-uniform and Asymptotic Confidence Sequence of Quantile under Local Differential Privacy
73. NeurIPS 2025TokenSwap: A Lightweight Method to Disrupt Memorized Sequences in LLMs
74. NeurIPS 2025Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
75. NeurIPS 2025Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks
76. NeurIPS 2025Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy
77. NeurIPS 2025Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
78. NeurIPS 2025Versatile Transferable Unlearnable Example Generator
79. NeurIPS 2025⁠When Data Can't Meet: Estimating Correlation Across Privacy Barriers
80. NeurIPS 2025You Only Communicate Once: One-shot Federated Low-Rank Adaptation of MLLM

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。