( events)   Timezone: »  
Tue Dec 14 08:10 AM -- 05:55 PM (PST)
Privacy in Machine Learning (PriML) 2021
Yu-Xiang Wang · Borja Balle · Giovanni Cherubin · Kamalika Chaudhuri · Antti Honkela · Jonathan Lebensold · Casey Meehan · Mi Jung Park · Adrian Weller · Yuqing Zhu

Workshop Home Page

The goal of our workshop is to bring together privacy experts working in academia and industry to discuss the present and future of technologies that enable machine learning with privacy. The workshop will focus on the technical aspects of privacy research and deployment with invited and contributed talks by distinguished researchers in the area. By design, the workshop should serve as a meeting point for regular NeurIPS attendees interested/working on privacy to meet other parts of the privacy community (security researchers, legal scholars, industry practitioners). The focus this year will include emerging problems such as machine unlearning, privacy-fairness tradeoffs and legal challenges in recent deployments of differential privacy (e.g. that of the US Census Bureau). We will conclude the workshop with a panel discussion titled: “Machine Learning and Privacy in Practice: Challenges, Pitfalls and Opportunities”. A diverse set of panelists will address the challenges faced applying these technologies to the real world. The programme of the workshop will emphasize the diversity of points of view on the problem of privacy. We will also ensure that there is ample time for discussions that encourage networking between researchers, which should result in mutually beneficial new long-term collaborations.

Invited talk: Helen Nissenbaum (Cornell Tech) --- Practical Privacy, Fairness, Ethics, Policy (Invited talk)
Contributed talk
Contributed talk
Coffee break (coffee break)
Invited talk: Emiliano de Cristofaro (University College London) --- Privacy in Machine Learning -- It's Complicated (Invited talk)
Contributed talk
Lunch Break (Break)
Invited talk: Kristin Lauter (Facebook AI Research): ML on Encrypted Data. (Invited talk)
Contributed talk
Contributed talk
Coffee break (Break)
Invited talk: Aaron Roth (UPenn / Amazon): Machine Unlearning. (Invited talk)
Closing (closing)
Canonical Noise Distributions and Private Hypothesis Tests (Poster)
A Generic Hybrid 2PC Framework with Application to Private Inference of Unmodified Neural Networks (Extended Abstract) (Poster)
Canonical Noise Distributions and Private Hypothesis Tests (Oral)
Label Private Deep Learning Training based on Secure Multiparty Computation and Differential Privacy (Poster)
Architecture Matters: Investigating the Influence of Differential Privacy on Neural Network Design (Poster)
Enforcing fairness in private federated learning via the modified method of differential multipliers (Poster)
Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods (Poster)
Tight Accounting in the Shuffle Model of Differential Privacy (Poster)
Combining Public and Private Data (Poster)
Opacus: User-Friendly Differential Privacy Library in PyTorch (Poster)
Certified Predictions using MPC-Friendly Publicly Verifiable Covertly Secure Commitments (Poster)
SoK: Privacy-preserving Clustering (Extended Abstract) (Oral)
ABY2.0: New Efficient Primitives for STPC with Applications to Privacy in Machine Learning (Extended Abstract) (Poster)
Membership Inference Attacks Against NLP Classification Models (Poster)
Differentially Private Hamiltonian Monte Carlo (Poster)
DP-SEP: Differentially private stochastic expectation propagation (Poster)
Simple Baselines Are Strong Performers for Differentially Private Natural Language Processing (Oral)
Poster Session (Gather.Town)
SSSE: Efficiently Erasing Samples from Trained Machine Learning Models (Poster)
Privacy-Aware Rejection Sampling (Oral)
Zero Knowledge Arguments for Verifiable Sampling (Poster)
Population Level Privacy Leakage in Binary Classification wtih Label Noise (Poster)
Mean Estimation with User-level Privacy under Data Heterogeneity (Poster)
Private Confidence Sets (Poster)
Realistic Face Reconstruction from Deep Embeddings (Poster)
Reconstructing Test Labels from Noisy Loss Scores (Extended Abstract) (Poster)
Characterizing and Improving MPC-based Private Inference for Transformer-based Models (Poster)
Differential Privacy via Group Shuffling (Oral)
Sample-and-threshold differential privacy: Histograms and applications (Poster)
Population Level Privacy Leakage in Binary Classification wtih Label Noise (Oral)
A Joint Exponential Mechanism for Differentially Private Top-k Set (Poster)
Unsupervised Membership Inference Attacks Against Machine Learning Models (Poster)
Differential Privacy via Group Shuffling (Poster)
Feature-level privacy loss modelling in differentially private machine learning (Poster)
Interaction data are identifiable even across long periods of time (Poster)
SoK: Privacy-preserving Clustering (Extended Abstract) (Poster)
Communication Efficient Federated Learning with Secure Aggregation and Differential Privacy (Poster)
Privacy-Aware Rejection Sampling (Poster)
Reconstructing Training Data with Informed Adversaries (Poster)
Basil: A Fast and Byzantine-Resilient Approach for Decentralized Training (Poster)
Adversarial Detection Avoidance Attacks: Evaluating the robustness of perceptual hashing-based client-side scanning (Poster)
An automatic differentiation system for the age of differential privacy (Poster)
Understanding Training-Data Leakage from Gradients in Neural Networks for ImageClassifications (Poster)
A Novel Self-Distillation Architecture to Defeat Membership Inference Attacks (Poster)
Efficient passive membership inference attack in federated learning (Poster)
Simple Baselines Are Strong Performers for Differentially Private Natural Language Processing (Poster)