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

431 papers, page 6 of 9

251. NeurIPS 2025Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy
252. NeurIPS 2025MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM Inference
253. NeurIPS 2025Multi-Class Support Vector Machine with Differential Privacy
254. NeurIPS 2025OASIS: One-Shot Federated Graph Learning via Wasserstein Assisted Knowledge Integration
255. NeurIPS 2025ObCLIP: Oblivious CLoud-Device Hybrid Image Generation with Privacy Preservation
256. NeurIPS 2025On the Sample Complexity of Differentially Private Policy Optimization
257. NeurIPS 2025OpenGU: A Comprehensive Benchmark for Graph Unlearning
258. NeurIPS 2025Optimal Best Arm Identification under Differential Privacy
259. NeurIPS 2025Optimal Regret of Bandits under Differential Privacy
260. NeurIPS 2025Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models
261. NeurIPS 2025Practical Bayes-Optimal Membership Inference Attacks
262. NeurIPS 2025Privacy amplification by random allocation
263. NeurIPS 2025Privacy Reasoning in Ambiguous Contexts
264. NeurIPS 2025Private Continual Counting of Unbounded Streams
265. NeurIPS 2025Private Geometric Median in Nearly-Linear Time
266. NeurIPS 2025Private Hyperparameter Tuning with Ex-Post Guarantee
267. NeurIPS 2025Private Set Union with Multiple Contributions
268. NeurIPS 2025Private Zeroth-Order Optimization with Public Data
269. NeurIPS 2025Probabilistic Reasoning with LLMs for Privacy Risk Estimation
270. NeurIPS 2025Purifying Approximate Differential Privacy with Randomized Post-processing
271. NeurIPS 2025Query-Efficient Locally Private Hypothesis Selection via the Scheffe Graph
272. NeurIPS 2025Rethinking Fair Federated Learning from Parameter and Client View
273. NeurIPS 2025Rethinking the Role of Verbatim Memorization in LLM Privacy
274. NeurIPS 2025Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions
275. NeurIPS 2025RUAGO: Effective and Practical Retain-Free Unlearning via Adversarial Attack and OOD Generator
276. NeurIPS 2025Second-Order Convergence in Private Stochastic Non-Convex Optimization
277. NeurIPS 2025Secure and Confidential Certificates of Online Fairness
278. NeurIPS 2025Sequentially Auditing Differential Privacy
279. NeurIPS 2025Setting $\varepsilon$ is not the Issue in Differential Privacy
280. NeurIPS 2025Sketched Gaussian Mechanism for Private Federated Learning
281. NeurIPS 2025Subgraph Federated Learning via Spectral Methods
282. NeurIPS 2025Sum Estimation under Personalized Local Differential Privacy
283. NeurIPS 2025Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries
284. NeurIPS 2025The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples
285. NeurIPS 2025Time-uniform and Asymptotic Confidence Sequence of Quantile under Local Differential Privacy
286. NeurIPS 2025TokenSwap: A Lightweight Method to Disrupt Memorized Sequences in LLMs
287. NeurIPS 2025Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
288. NeurIPS 2025Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks
289. NeurIPS 2025Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy
290. NeurIPS 2025Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
291. NeurIPS 2025Versatile Transferable Unlearnable Example Generator
292. NeurIPS 2025⁠When Data Can't Meet: Estimating Correlation Across Privacy Barriers
293. NeurIPS 2025You Only Communicate Once: One-shot Federated Low-Rank Adaptation of MLLM
294. CVPR 2024DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection
295. CVPR 2024Efficient Privacy-Preserving Visual Localization Using 3D Ray Clouds
296. CVPR 2024FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning
297. CVPR 2024Privacy-Preserving Face Recognition Using Trainable Feature Subtraction
298. CVPR 2024Privacy-Preserving Optics for Enhancing Protection in Face De-Identification
299. CVPR 2024Validating Privacy-Preserving Face Recognition under a Minimum Assumption
300. ICLR 2024Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for 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.