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 155 篇，第 2 / 4 页

51. ICML 2025Optimal Survey Design for Private Mean Estimation
52. ICML 2025Optimizing Noise Distributions for Differential Privacy
53. ICML 2025PASS: Private Attributes Protection with Stochastic Data Substitution
54. ICML 2025PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative APIs
55. ICML 2025Plausible Token Amplification for Improving Accuracy of Differentially Private In-Context Learning Based on Implicit Bayesian Inference
56. ICML 2025Position: Contextual Integrity is Inadequately Applied to Language Models
57. ICML 2025Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting
58. ICML 2025Privacy Amplification Through Synthetic Data: Insights from Linear Regression
59. ICML 2025Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation
60. ICML 2025Private Federated Learning using Preference-Optimized Synthetic Data
61. ICML 2025Private Lossless Multiple Release
62. ICML 2025Private Model Personalization Revisited
63. ICML 2025Rethinking the Temperature for Federated Heterogeneous Distillation
64. ICML 2025Scalable Private Partition Selection via Adaptive Weighting
65. ICML 2025Scaling Laws for Differentially Private Language Models
66. ICML 2025SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large Embedding
67. ICML 2025Synthetic Face Datasets Generation via Latent Space Exploration from Brownian Identity Diffusion
68. ICML 2025Textual Unlearning Gives a False Sense of Unlearning
69. ICML 2025Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models
70. ICML 2025Towards Trustworthy Federated Learning with Untrusted Participants
71. ICML 2025Tracking The Best Expert Privately
72. ICML 2025Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning
73. ICML 2025Variance as a Catalyst: Efficient and Transferable Semantic Erasure Adversarial Attack for Customized Diffusion Models
74. ICML 2025Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models
75. ICML 2025XAttnMark: Learning Robust Audio Watermarking with Cross-Attention
76. NeurIPS 2025A Generalized Binary Tree Mechanism for Private Approximation of All-Pair Shortest Distances
77. NeurIPS 2025A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable Input
78. NeurIPS 2025A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation
79. NeurIPS 2025Adaptive Data Analysis for Growing Data
80. NeurIPS 2025Adaptive Sigmoid Clipping for Balancing the Direction–Magnitude Mismatch Trade-off in Differentially Private Learning
81. NeurIPS 2025AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents
82. NeurIPS 2025An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise
83. NeurIPS 2025Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools
84. NeurIPS 2025Can We Infer Confidential Properties of Training Data from LLMs?
85. NeurIPS 2025Continual Release Moment Estimation with Differential Privacy
86. NeurIPS 2025Controlling The Spread of Epidemics on Networks with Differential Privacy
87. NeurIPS 2025Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy
88. NeurIPS 2025CryptoMoE: Privacy-Preserving and Scalable Mixture of Experts Inference via Balanced Expert Routing
89. NeurIPS 2025Data-Free Model Extraction for Black-box Recommender Systems via Graph Convolutions
90. NeurIPS 2025Deep Learning with Plausible Deniability
91. NeurIPS 2025DictPFL: Efficient and Private Federated Learning on Encrypted Gradients
92. NeurIPS 2025Differential Privacy for Euclidean Jordan Algebra with Applications to Private Symmetric Cone Programming
93. NeurIPS 2025Differential Privacy on Fully Dynamic Streams
94. NeurIPS 2025Differentially Private Bilevel Optimization: Efficient Algorithms with Near-Optimal Rates
95. NeurIPS 2025Differentially Private Gomory-Hu Trees
96. NeurIPS 2025Differentially Private High-dimensional Variable Selection via Integer Programming
97. NeurIPS 2025Differentially Private Quantiles with Smaller Error
98. NeurIPS 2025Differentially Private Relational Learning with Entity-level Privacy Guarantees
99. NeurIPS 2025DKDR: Dynamic Knowledge Distillation for Reliability in Federated Learning
100. NeurIPS 2025Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data

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。