( events)   Timezone: »  
Fri Dec 11 01:20 AM -- 01:25 PM (PST)
Privacy Preserving Machine Learning - PriML and PPML Joint Edition
Borja Balle · James Bell · Aurélien Bellet · Kamalika Chaudhuri · Adria Gascon · Antti Honkela · Antti Koskela · Casey Meehan · Olga Ohrimenko · Mi Jung Park · Mariana Raykova · Mary Anne Smart · Yu-Xiang Wang · Adrian Weller

Workshop Home Page

This one day workshop focuses on privacy preserving techniques for machine learning and disclosure in large scale data analysis, both in the distributed and centralized settings, and on scenarios that highlight the importance and need for these techniques (e.g., via privacy attacks). There is growing interest from the Machine Learning (ML) community in leveraging cryptographic techniques such as Multi-Party Computation (MPC) and Homomorphic Encryption (HE) for privacy preserving training and inference, as well as Differential Privacy (DP) for disclosure. Simultaneously, the systems security and cryptography community has proposed various secure frameworks for ML. We encourage both theory and application-oriented submissions exploring a range of approaches listed below. Additionally, given the tension between the adoption of machine learning technologies and ethical, technical and regulatory issues about privacy, as highlighted during the COVID-19 pandemic, we invite submissions for the special track on this topic.

Welcome & Introduction (Live Intro)
Invited Talk #1: Reza Shokri (National University of Singapore) (Invited Talk)
Invited Talk #2: Katrina Ligett (Hebrew University) (Invited Talk)
Invited Talk Q&A with Reza and Katrina (Q&A Session)
Contributed Talk #1: POSEIDON: Privacy-Preserving Federated Neural Network Learning (Oral)
Contributed Talk Q&A (Q&A Session)
Poster Session & Social on Gather.Town (Poster Session)
Welcome & Introduction (Live Intro)
Invited Talk #3: Carmela Troncoso (EPFL) (Invited Talk)
Invited Talk #4: Dan Boneh (Stanford University) (Invited Talk)
Invited Talk Q&A with Carmela and Dan (Q&A Session)
Poster Session & Social on Gather.Town (Poster Session)
Contributed Talk #2: On the (Im)Possibility of Private Machine Learning through Instance Encoding (Oral)
Contributed Talk #3: Poirot: Private Contact Summary Aggregation (Oral)
Contributed Talk #4: Greenwoods: A Practical Random Forest Framework for Privacy Preserving Training and Prediction (Oral)
Contributed Talks Q&A (Q&A Session)
Contributed Talk #5: Shuffled Model of Federated Learning: Privacy, Accuracy, and Communication Trade-offs (Oral)
Contributed Talk #6: Sample-efficient proper PAC learning with approximate differential privacy (Oral)
Contributed Talk #7: Training Production Language Models without Memorizing User Data (Oral)
Contributed Talks Q&A (Q&A Session)
Privacy in Multi-armed Bandits: Fundamental Definitions and Lower Bounds on Regret (Poster)
CrypTen: Secure Multi-Party Computation Meets Machine Learning (Poster)
Twinify: A software package for differentially private data release (Poster)
Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling (Poster)
Dataset Inference: Ownership Resolution in Machine Learning (Poster)
Privacy-preserving XGBoost Inference (Poster)
Differentially Private Generative Models Through Optimal Transport (Poster)
PrivAttack: A Membership Inference AttackFramework Against Deep Reinforcement LearningAgents (Poster)
Effectiveness of MPC-friendly Softmax Replacement (Poster)
Accuracy, Interpretability and Differential Privacy via Explainable Boosting (Poster)
Differentially private cross-silo federated learning (Poster)
On the Sample Complexity of Privately Learning Unbounded High-Dimensional Gaussians (Poster)
Secure Single-Server Aggregation with (Poly)Logarithmic Overhead (Poster)
Understanding Unintended Memorization in Federated Learning (Poster)
Local Differentially Private Regret Minimization in Reinforcement Learning (Poster)
SOTERIA: In Search of Efficient Neural Networks for Private Inference (Poster)
Fairness in the Eyes of the Data: Certifying Machine-Learning Models (Poster)
SWIFT: Super-fast and Robust Privacy-Preserving Machine Learning (Poster)
Does Domain Generalization Provide Inherent Membership Privacy (Poster)
Characterizing Private Clipped Gradient Descent on Convex Generalized Linear Problems (Poster)
Distributed Differentially Private Averaging with Improved Utility and Robustness to Malicious Parties (Poster)
Robustness Threats of Differential Privacy (Poster)
Asymmetric Private Set Intersection with Applications to Contact Tracing and Private Vertical Federated Machine Learning (Poster)
Generative Adversarial User Privacy in Lossy Single-Server Information Retrieval (Poster)
Data Appraisal Without Data Sharing (Poster)
Network Generation with Differential Privacy (Poster)
On Polynomial Approximations for Privacy-Preserving and Verifiable ReLU Networks (Poster)
Quantifying Privacy Leakage in Graph Embedding (Poster)
Machine Learning with Membership Privacy via Knowledge Transfer (Poster)
Privacy Amplification by Decentralization (Poster)
Challenges of Differentially Private Prediction in Healthcare Settings (Poster)
Privacy Risks in Embedded Deep Learning (Poster)
Dynamic Channel Pruning for Privacy (Poster)
Randomness Beyond Noise: Differentially Private Optimization Improvement through Mixup (Poster)
Adversarial Attacks and Countermeasures on Private Training in MPC (Poster)
Privacy Preserving Chatbot Conversations (Poster)
Revisiting Membership Inference Under Realistic Assumptions (Poster)
Tight Approximate Differential Privacy for Discrete-Valued Mechanisms Using FFT (Poster)
Enabling Fast Differentially Private SGD via Static Graph Compilation and Batch-Level Parallelism (Poster)
Robust and Private Learning of Halfspaces (Poster)
DAMS: Meta-estimation of private sketch data structures for differentially private contact tracing (Poster)
Individual Privacy Accounting via a Rényi Filter (Poster)
SparkFHE: Distributed Dataflow Framework with Fully Homomorphic Encryption (Poster)
MP2ML: A Mixed-Protocol Machine LearningFramework for Private Inference (Poster)
Data-oblivious training for XGBoost models (Poster)
Towards General-purpose Infrastructure for Protecting Scientific Data Under Study (Poster)
Differentially Private Stochastic Coordinate Descent (Poster)
New Challenges for Fully Homomorphic Encryption (Poster)
Mitigating Leakage in Federated Learning with Trusted Hardware (Poster)
A Principled Approach to Learning Stochastic Representations for Privacy in Deep Neural Inference (Poster)
Privacy Regularization: Joint Privacy-Utility Optimization in Language Models (Poster)
Privacy Attacks on Machine Unlearning (Poster)
Multi-Headed Global Model for handling Non-IID data (Poster)
Secure Medical Image Analysis with CrypTFlow (Poster)
Differentially Private Bayesian Inference For GLMs (Poster)
Optimal Client Sampling for Federated Learning (Poster)
DYSAN: Dynamically sanitizing motion sensor data against sensitive inferences through adversarial networks (Poster)
Unifying Privacy Loss for Data Analytics (Poster)