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 5 / 9 页

201. ICML 2025Rethinking the Temperature for Federated Heterogeneous Distillation
202. ICML 2025Scalable Private Partition Selection via Adaptive Weighting
203. ICML 2025Scaling Laws for Differentially Private Language Models
204. ICML 2025SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large Embedding
205. ICML 2025Synthetic Face Datasets Generation via Latent Space Exploration from Brownian Identity Diffusion
206. ICML 2025Textual Unlearning Gives a False Sense of Unlearning
207. ICML 2025Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models
208. ICML 2025Towards Trustworthy Federated Learning with Untrusted Participants
209. ICML 2025Tracking The Best Expert Privately
210. ICML 2025Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning
211. ICML 2025Variance as a Catalyst: Efficient and Transferable Semantic Erasure Adversarial Attack for Customized Diffusion Models
212. ICML 2025Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models
213. ICML 2025XAttnMark: Learning Robust Audio Watermarking with Cross-Attention
214. NeurIPS 2025A Generalized Binary Tree Mechanism for Private Approximation of All-Pair Shortest Distances
215. NeurIPS 2025A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable Input
216. NeurIPS 2025A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation
217. NeurIPS 2025Adaptive Data Analysis for Growing Data
218. NeurIPS 2025Adaptive Sigmoid Clipping for Balancing the Direction–Magnitude Mismatch Trade-off in Differentially Private Learning
219. NeurIPS 2025AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents
220. NeurIPS 2025An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise
221. NeurIPS 2025Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools
222. NeurIPS 2025Can We Infer Confidential Properties of Training Data from LLMs?
223. NeurIPS 2025Continual Release Moment Estimation with Differential Privacy
224. NeurIPS 2025Controlling The Spread of Epidemics on Networks with Differential Privacy
225. NeurIPS 2025Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy
226. NeurIPS 2025CryptoMoE: Privacy-Preserving and Scalable Mixture of Experts Inference via Balanced Expert Routing
227. NeurIPS 2025Data-Free Model Extraction for Black-box Recommender Systems via Graph Convolutions
228. NeurIPS 2025Deep Learning with Plausible Deniability
229. NeurIPS 2025DictPFL: Efficient and Private Federated Learning on Encrypted Gradients
230. NeurIPS 2025Differential Privacy for Euclidean Jordan Algebra with Applications to Private Symmetric Cone Programming
231. NeurIPS 2025Differential Privacy on Fully Dynamic Streams
232. NeurIPS 2025Differentially Private Bilevel Optimization: Efficient Algorithms with Near-Optimal Rates
233. NeurIPS 2025Differentially Private Gomory-Hu Trees
234. NeurIPS 2025Differentially Private High-dimensional Variable Selection via Integer Programming
235. NeurIPS 2025Differentially Private Quantiles with Smaller Error
236. NeurIPS 2025Differentially Private Relational Learning with Entity-level Privacy Guarantees
237. NeurIPS 2025DKDR: Dynamic Knowledge Distillation for Reliability in Federated Learning
238. NeurIPS 2025Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data
239. NeurIPS 2025DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents
240. NeurIPS 2025Exploring the limits of strong membership inference attacks on large language models
241. NeurIPS 2025FedRW: Efficient Privacy-Preserving Data Reweighting for Enhancing Federated Learning of Language Models
242. NeurIPS 2025FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts
243. NeurIPS 2025FracFace: Breaking The Visual Clues—Fractal-Based Privacy-Preserving Face Recognition
244. NeurIPS 2025GeoClip: Geometry-Aware Clipping for Differentially Private SGD
245. NeurIPS 2025Harnessing the Universal Geometry of Embeddings
246. NeurIPS 2025How Well Can Differential Privacy Be Audited in One Run?
247. NeurIPS 2025Instance-Optimality for Private KL Distribution Estimation
248. NeurIPS 2025InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy
249. NeurIPS 2025Locally Optimal Private Sampling: Beyond the Global Minimax
250. NeurIPS 2025Machine Unlearning via Task Simplex Arithmetic

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。