Social aspects · privacy papers, 2023–2026

Key findings

• Social aspects · privacy went from 21 papers in 2023 to 138 in 2026, roughly 6.6x in three years.
• NeurIPS publishes the most Social aspects · privacy work: 215 papers from 2023 to 2026, 50% of the four-venue total.
• The fastest-growing overlap is with Social aspects · accountability transparency and interpretability: papers tagged with both rose from 0 in 2023 to 93 in 2026.
• Among the 5 topics under Alignment and Responsible AI, it ranks #4 by 2026 paper count; the fastest grower in the group, Social aspects · safety, is up 93x versus 6.6x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Social aspects · privacy papers

117 papers, page 2 of 3

51. NeurIPS 2024Disentangled Style Domain for Implicit $z$-Watermark Towards Copyright Protection
52. NeurIPS 2024DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction
53. NeurIPS 2024Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning
54. NeurIPS 2024Efficient and Private Marginal Reconstruction with Local Non-Negativity
55. NeurIPS 2024Exactly Minimax-Optimal Locally Differentially Private Sampling
56. NeurIPS 2024Faster Algorithms for User-Level Private Stochastic Convex Optimization
57. NeurIPS 2024Faster Differentially Private Top-$k$ Selection: A Joint Exponential Mechanism with Pruning
58. NeurIPS 2024Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning
59. NeurIPS 2024Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups
60. NeurIPS 2024Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity
61. NeurIPS 2024FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detection
62. NeurIPS 2024FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Space
63. NeurIPS 2024GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting
64. NeurIPS 2024Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Images
65. NeurIPS 2024GS-Hider: Hiding Messages into 3D Gaussian Splatting
66. NeurIPS 2024HEPrune: Fast Private Training of Deep Neural Networks With Encrypted Data Pruning
67. NeurIPS 2024Instance-Optimal Private Density Estimation in the Wasserstein Distance
68. NeurIPS 2024Instance-Specific Asymmetric Sensitivity in Differential Privacy
69. NeurIPS 2024Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
70. NeurIPS 2024Large Language Model Unlearning
71. NeurIPS 2024Measuring Dejavu Memorization Efficiently
72. NeurIPS 2024Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
73. NeurIPS 2024Membership Inference Attacks against Large Vision-Language Models
74. NeurIPS 2024Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
75. NeurIPS 2024Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
76. NeurIPS 2024Nimbus: Secure and Efficient Two-Party Inference for Transformers
77. NeurIPS 2024No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices
78. NeurIPS 2024Noise-Aware Differentially Private Regression via Meta-Learning
79. NeurIPS 2024Noisy Dual Mirror Descent: A Near Optimal Algorithm for Jointly-DP Convex Resource Allocation
80. NeurIPS 2024On Differentially Private Subspace Estimation in a Distribution-Free Setting
81. NeurIPS 2024On Differentially Private U Statistics
82. NeurIPS 2024On provable privacy vulnerabilities of graph representations
83. NeurIPS 2024On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift
84. NeurIPS 2024On the Computational Complexity of Private High-dimensional Model Selection
85. NeurIPS 2024Oracle-Efficient Differentially Private Learning with Public Data
86. NeurIPS 2024OSLO: One-Shot Label-Only Membership Inference Attacks
87. NeurIPS 2024PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
88. NeurIPS 2024Pre-training Differentially Private Models with Limited Public Data
89. NeurIPS 2024Prior-itizing Privacy: A Bayesian Approach to Setting the Privacy Budget in Differential Privacy
90. NeurIPS 2024Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
91. NeurIPS 2024Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training
92. NeurIPS 2024PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
93. NeurIPS 2024Private and Personalized Frequency Estimation in a Federated Setting
94. NeurIPS 2024Private Attribute Inference from Images with Vision-Language Models
95. NeurIPS 2024Private Edge Density Estimation for Random Graphs: Optimal, Efficient and Robust
96. NeurIPS 2024Private Geometric Median
97. NeurIPS 2024Private Online Learning via Lazy Algorithms
98. NeurIPS 2024Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions
99. NeurIPS 2024PrivCirNet: Efficient Private Inference via Block Circulant Transformation
100. NeurIPS 2024Pseudo-Private Data Guided Model Inversion Attacks

FAQ

How many Social aspects · privacy papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

431 in total: 21 in 2023, 117 in 2024, 155 in 2025, 138 in 2026.

How many Social aspects · privacy papers are at NeurIPS 2026?

NeurIPS 2026 has 44 Social aspects · privacy papers, versus 80 the year before.

How many Social aspects · privacy papers are at ICLR 2026?

ICLR 2026 has 2 Social aspects · privacy papers, versus 2 the year before.

How many Social aspects · privacy papers are at ICML 2026?

ICML 2026 has 90 Social aspects · privacy papers, versus 71 the year before.

How many Social aspects · privacy papers are at CVPR 2026?

CVPR 2026 has 2 Social aspects · privacy papers, versus 2 the year before.

Which conference publishes the most Social aspects · privacy papers?

NeurIPS, with 215 papers from 2023 to 2026.