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 3 / 9 页

101. NeurIPS 2026Benchmarking Membership Privacy Risks in Preference-Based LLM Post-Training
102. NeurIPS 2026Causal Evaluation of Membership Inference Attacks
103. NeurIPS 2026Detecting Hidden ML Training With Zero-Overhead Telemetry
104. NeurIPS 2026DP-EGGROLL: Centered Fitness-Vector Privatization for Backprop-Free Differentially Private Optimization
105. NeurIPS 2026DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
106. NeurIPS 2026Efficient Label Distribution Inference Attack and Defense on Classifier Weights in Federated Learning
107. NeurIPS 2026ERIS: Enhancing Privacy and Scalability in Federated Learning via Federated Shard Aggregation
108. NeurIPS 2026𝑓-Differential Privacy Filters: Validity and Approximate Solutions
109. NeurIPS 2026Federated Concept-Based Models: Interpretable models with distributed supervision
110. NeurIPS 2026FILOsofer: A TEE-Shielded Model Partitioning Framework based on Fisher Information-Guided LoRA Obfuscation
111. NeurIPS 2026GOLIATH: Gradient Inversion of Tabular Diffusion Models
112. NeurIPS 2026How Far Are VLMs from Privacy Awareness in the Physical World? An Empirical Study
113. NeurIPS 2026Jaguar: Fast Private CNN Inference with Power-of-Two Homomorphic Arithmetic
114. NeurIPS 2026Learning the Signature of Memorization in Autoregressive Language Models
115. NeurIPS 2026Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning
116. NeurIPS 2026Lumberjack: Better Differentially Private Random Forests through Heavy Hitter Detection in Trees
117. NeurIPS 2026Mitigating Memorization Where It Happens
118. NeurIPS 2026Models Designed to Forget: Machine Unlearning via Key Deletion
119. NeurIPS 2026MPCI-Bench: A Benchmark for Multimodal Pairwise Contextual Integrity Privacy Evaluation of Language Model Agents
120. NeurIPS 2026On Differentially Private Mechanisms for Linear Regression
121. NeurIPS 2026On Inherent Privacy of Posterior Sampling: A Unified R\'enyi-Divergence Framework
122. NeurIPS 2026Online Differentially Private Consistent Clustering
123. NeurIPS 2026Optimal Algorithms for Fixed-Graph Multi-Attribution Privacy
124. NeurIPS 2026Optimal Rates for Adaptive Private $k$-PCA
125. NeurIPS 2026Optimal Rates for Differentially Private Hypothesis Testing with E-values
126. NeurIPS 2026PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization
127. NeurIPS 2026Position: Life-Logging Video Streams Make the Privacy–Utility Trade-off Inevitable
128. NeurIPS 2026Privacy Amplification Persists under Unlimited Synthetic Data Release
129. NeurIPS 2026Privacy by Postprocessing the Discrete Laplace Mechanism
130. NeurIPS 2026Privacy Meets Hierarchy: Differentially Private Distributed Trilevel Learning
131. NeurIPS 2026Privacy Risk Scales with Effective Dimension in Federated Learning
132. NeurIPS 2026PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior
133. NeurIPS 2026Private Online Prediction from Experts with Small Losses
134. NeurIPS 2026Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation
135. NeurIPS 2026Sequential Membership Inference Attacks
136. NeurIPS 2026Sort, Partition, Randomize: Optimal Binary Hypothesis Testing under Local Differential Privacy
137. NeurIPS 2026The BatchNorm Illusion: Diagnosing Normalization Artifacts in Machine Unlearning Evaluation
138. NeurIPS 2026Understanding Private Evolution as Learning-Augmented Clustering
139. CVPR 2025Enhancing Facial Privacy Protection via Weakening Diffusion Purification
140. CVPR 2025Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models
141. ICLR 2025Machine Unlearning via Simulated Oracle Matching
142. ICLR 2025Privacy-Aware Lifelong Learning
143. ICML 2025A Certified Unlearning Approach without Access to Source Data
144. ICML 2025A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO
145. ICML 2025Adapting to Linear Separable Subsets with Large-Margin in Differentially Private Learning
146. ICML 2025An Efficient Private GPT Never Autoregressively Decodes
147. ICML 2025Approximate Differential Privacy of the $\ell_2$ Mechanism
148. ICML 2025Auditing $f$-differential privacy in one run
149. ICML 2025Auditing Prompt Caching in Language Model APIs
150. ICML 2025Breaking the $n^{1.5}$ Additive Error Barrier for Private and Efficient Graph Sparsification via Private Expander Decomposition

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。