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 7 / 9 页

301. ICLR 2024Beyond Memorization: Violating Privacy via Inference with Large Language Models
302. ICLR 2024Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
303. ICLR 2024DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
304. ICLR 2024FedInverse: Evaluating Privacy Leakage in Federated Learning
305. ICLR 2024Improved Analysis of Sparse Linear Regression in Local Differential Privacy Model
306. ICLR 2024LabelDP-Pro: Learning with Label Differential Privacy via Projections
307. ICLR 2024Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions
308. ICLR 2024Privacy Amplification for Matrix Mechanisms
309. ICLR 2024Privacy-Preserving In-Context Learning for Large Language Models
310. ICLR 2024Unprocessing Seven Years of Algorithmic Fairness
311. ICML 2024Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy
312. ICML 2024Mean Estimation in the Add-Remove Model of Differential Privacy
313. ICML 2024Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss
314. ICML 2024Neural Collapse meets Differential Privacy: Curious behaviors of NoisyGD with Near-Perfect Representation Learning
315. ICML 2024Privacy Attacks in Decentralized Learning
316. ICML 2024Privacy Backdoors: Stealing Data with Corrupted Pretrained Models
317. ICML 2024Privacy Preserving Adaptive Experiment Design
318. ICML 2024Privacy Profiles for Private Selection
319. ICML 2024Privacy-Preserving Embedding via Look-up Table Evaluation with Fully Homomorphic Encryption
320. ICML 2024Provable Privacy with Non-Private Pre-Processing
321. ICML 2024Shifted Interpolation for Differential Privacy
322. ICML 2024The Privacy Power of Correlated Noise in Decentralized Learning
323. ICML 2024Transferable Facial Privacy Protection against Blind Face Restoration via Domain-Consistent Adversarial Obfuscation
324. NeurIPS 2024A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy
325. NeurIPS 2024A Synthetic Dataset for Personal Attribute Inference
326. NeurIPS 2024Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
327. NeurIPS 2024Attack-Aware Noise Calibration for Differential Privacy
328. NeurIPS 2024Auditing Privacy Mechanisms via Label Inference Attacks
329. NeurIPS 2024Banded Square Root Matrix Factorization for Differentially Private Model Training
330. NeurIPS 2024Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment Approach
331. NeurIPS 2024Certified Machine Unlearning via Noisy Stochastic Gradient Descent
332. NeurIPS 2024Continual Counting with Gradual Privacy Expiration
333. NeurIPS 2024Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature
334. NeurIPS 2024DAGER: Exact Gradient Inversion for Large Language Models
335. NeurIPS 2024DataStealing: Steal Data from Diffusion Models in Federated Learning with Multiple Trojans
336. NeurIPS 2024Déjà Vu Memorization in Vision–Language Models
337. NeurIPS 2024Differential Privacy in Scalable General Kernel Learning via $K$-means Nystr{\"o}m Random Features
338. NeurIPS 2024Differentially Private Equivalence Testing for Continuous Distributions and Applications
339. NeurIPS 2024Differentially Private Optimization with Sparse Gradients
340. NeurIPS 2024Differentially Private Reinforcement Learning with Self-Play
341. NeurIPS 2024Differentially Private Set Representations
342. NeurIPS 2024Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement
343. NeurIPS 2024Dimension-free Private Mean Estimation for Anisotropic Distributions
344. NeurIPS 2024Disentangled Style Domain for Implicit $z$-Watermark Towards Copyright Protection
345. NeurIPS 2024DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction
346. NeurIPS 2024Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning
347. NeurIPS 2024Efficient and Private Marginal Reconstruction with Local Non-Negativity
348. NeurIPS 2024Exactly Minimax-Optimal Locally Differentially Private Sampling
349. NeurIPS 2024Faster Algorithms for User-Level Private Stochastic Convex Optimization
350. NeurIPS 2024Faster Differentially Private Top-$k$ Selection: A Joint Exponential Mechanism with Pruning

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。