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 3 / 4 页

101. NeurIPS 2025DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents
102. NeurIPS 2025Exploring the limits of strong membership inference attacks on large language models
103. NeurIPS 2025FedRW: Efficient Privacy-Preserving Data Reweighting for Enhancing Federated Learning of Language Models
104. NeurIPS 2025FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts
105. NeurIPS 2025FracFace: Breaking The Visual Clues—Fractal-Based Privacy-Preserving Face Recognition
106. NeurIPS 2025GeoClip: Geometry-Aware Clipping for Differentially Private SGD
107. NeurIPS 2025Harnessing the Universal Geometry of Embeddings
108. NeurIPS 2025How Well Can Differential Privacy Be Audited in One Run?
109. NeurIPS 2025Instance-Optimality for Private KL Distribution Estimation
110. NeurIPS 2025InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy
111. NeurIPS 2025Locally Optimal Private Sampling: Beyond the Global Minimax
112. NeurIPS 2025Machine Unlearning via Task Simplex Arithmetic
113. NeurIPS 2025Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy
114. NeurIPS 2025MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM Inference
115. NeurIPS 2025Multi-Class Support Vector Machine with Differential Privacy
116. NeurIPS 2025OASIS: One-Shot Federated Graph Learning via Wasserstein Assisted Knowledge Integration
117. NeurIPS 2025ObCLIP: Oblivious CLoud-Device Hybrid Image Generation with Privacy Preservation
118. NeurIPS 2025On the Sample Complexity of Differentially Private Policy Optimization
119. NeurIPS 2025OpenGU: A Comprehensive Benchmark for Graph Unlearning
120. NeurIPS 2025Optimal Best Arm Identification under Differential Privacy
121. NeurIPS 2025Optimal Regret of Bandits under Differential Privacy
122. NeurIPS 2025Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models
123. NeurIPS 2025Practical Bayes-Optimal Membership Inference Attacks
124. NeurIPS 2025Privacy amplification by random allocation
125. NeurIPS 2025Privacy Reasoning in Ambiguous Contexts
126. NeurIPS 2025Private Continual Counting of Unbounded Streams
127. NeurIPS 2025Private Geometric Median in Nearly-Linear Time
128. NeurIPS 2025Private Hyperparameter Tuning with Ex-Post Guarantee
129. NeurIPS 2025Private Set Union with Multiple Contributions
130. NeurIPS 2025Private Zeroth-Order Optimization with Public Data
131. NeurIPS 2025Probabilistic Reasoning with LLMs for Privacy Risk Estimation
132. NeurIPS 2025Purifying Approximate Differential Privacy with Randomized Post-processing
133. NeurIPS 2025Query-Efficient Locally Private Hypothesis Selection via the Scheffe Graph
134. NeurIPS 2025Rethinking Fair Federated Learning from Parameter and Client View
135. NeurIPS 2025Rethinking the Role of Verbatim Memorization in LLM Privacy
136. NeurIPS 2025Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions
137. NeurIPS 2025RUAGO: Effective and Practical Retain-Free Unlearning via Adversarial Attack and OOD Generator
138. NeurIPS 2025Second-Order Convergence in Private Stochastic Non-Convex Optimization
139. NeurIPS 2025Secure and Confidential Certificates of Online Fairness
140. NeurIPS 2025Sequentially Auditing Differential Privacy
141. NeurIPS 2025Setting $\varepsilon$ is not the Issue in Differential Privacy
142. NeurIPS 2025Sketched Gaussian Mechanism for Private Federated Learning
143. NeurIPS 2025Subgraph Federated Learning via Spectral Methods
144. NeurIPS 2025Sum Estimation under Personalized Local Differential Privacy
145. NeurIPS 2025Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries
146. NeurIPS 2025The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples
147. NeurIPS 2025Time-uniform and Asymptotic Confidence Sequence of Quantile under Local Differential Privacy
148. NeurIPS 2025TokenSwap: A Lightweight Method to Disrupt Memorized Sequences in LLMs
149. NeurIPS 2025Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
150. NeurIPS 2025Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks

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。