( events)   Timezone: »  
The 2020 schedule is still incomplete Program Highlights »
Fri Dec 11 12:00 AM -- 09:25 AM (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.

Invited talk #1: Reza Shokri (National University of Singapore) (Talk)
Reza Shokri
Invited talk #2: Carmela Troncoso (EPFL) (Talk)
Carmela Troncoso
Invited talk #3: Katrina Ligett (Hebrew University) (Talk)
Katrina Ligett
Invited talk #4: Dan Boneh (Stanford University) (Talk)
Dan Boneh
Robust and Private Learning of Halfspaces (Poster)
Badih Ghazi
Randomness Beyond Noise: Differentially Private Optimization Improvement through Mixup (Poster)
Hanshen Xiao
Distributed Differentially Private Averaging with Improved Utility and Robustness to Malicious Parties (Poster)
Aurélien Bellet
DAMS: Meta-estimation of private sketch data structures for differentially private contact tracing (Poster)
Praneeth Vepakomma
Individual Privacy Accounting via a Rényi Filter (Poster)
Vitaly Feldman
Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling (Poster)
Vitaly Feldman
SparkFHE: Distributed Dataflow Framework with Fully Homomorphic Encryption (Poster)
Peizhao Hu
SWIFT: Super-fast and Robust Privacy-Preserving Machine Learning (Poster)
Nishat Koti
MP2ML: A Mixed-Protocol Machine LearningFramework for Private Inference (Poster)
Fabian Boemer
Robustness Threats of Differential Privacy (Poster)
Ivan Oseledets
Adversarial Attacks and Countermeasures on Private Training in MPC (Poster)
Matthew Jagielski
Accuracy, Interpretability and Differential Privacy via Explainable Boosting (Poster)
Harsha Nori
Data-oblivious training for XGBoost models (Poster)
Chester Leung
Greenwoods: A Practical Random Forest Framework for Privacy Preserving Training and Prediction (Oral)
Harsh Chaudhari
Training Production Language Models without Memorizing User Data (Oral)
Swaroop Ramaswamy
Generative Adversarial User Privacy in Lossy Single-Server Information Retrieval (Poster)
Chung-Wei Weng
POSEIDON: Privacy-Preserving Federated Neural Network Learning (Oral)
Sinem Sav
Towards General-purpose Infrastructure for Protecting Scientific Data Under Study (Poster)
Kritika Prakash
Privacy Preserving Chatbot Conversations (Poster)
Debmalya Biswas
Differentially Private Stochastic Coordinate Descent (Poster)
Celestine Mendler-Dünner
Twinify: A software package for differentially private data release (Poster)
Joonas Jälkö
Dataset Inference: Ownership Resolution in Machine Learning (Poster)
Nicolas Papernot
Data Appraisal Without Data Sharing (Poster)
Mimee Xu
Privacy-preserving XGBoost Inference (Poster)
Xianrui Meng
New Challenges for Fully Homomorphic Encryption (Poster)
Marc Joye
Mitigating Leakage in Federated Learning with Trusted Hardware (Poster)
Javad Ghareh Chamani
Asymmetric Private Set Intersection with Applications to Contact Tracing and Private Vertical Federated Machine Learning (Poster)
Bogdan Cebere
Not All Features Are Equal: DiscoveringEssential Features for Preserving Prediction Privacy (Poster)
FatemehSadat Mireshghallah
PrivAttack: A Membership Inference AttackFramework Against Deep Reinforcement LearningAgents (Poster)
maziar gomrokchi
Revisiting Membership Inference Under Realistic Assumptions (Poster)
Bargav Jayaraman
Effectiveness of MPC-friendly Softmax Replacement (Poster)
Marcel Keller
Privacy Regularization: Joint Privacy-UtilityOptimization in Language Models (Poster)
FatemehSadat Mireshghallah
Tight Approximate Differential Privacy for Discrete-Valued Mechanisms Using FFT (Poster)
Antti Koskela
Network Generation with Differential Privacy (Poster)
Xu Zheng
Differentially private cross-silo federated learning (Poster)
Mikko Heikkilä
Privacy Attacks on Machine Unlearning (Poster)
Ji Gao
On Polynomial Approximations for Privacy-Preserving and Verifiable ReLU Networks (Poster)
Salman Avestimehr
On the Sample Complexity of Privately Learning Unbounded High-Dimensional Gaussians (Poster)
Ishaq Aden-Ali
Multi-Headed Global Model for handling Non-IID data (Poster)
Himanshu Arora
Secure Medical Image Analysis with CrypTFlow (Poster)
Javier Alvarez-Valle
Quantifying Privacy Leakage in Graph Embedding (Poster)
Antoine Boutet
Differentially Private Bayesian Inference For GLMs (Poster)
Joonas Jälkö
Optimal Client Sampling for Federated Learning (Poster)
Samuel Horváth
DYSAN: Dynamically sanitizing motion sensor data against sensitive inferences through adversarial networks (Poster)
Privacy Amplification by Decentralization (Poster)
Aurélien Bellet
Machine Learning with Membership Privacy via Knowledge Transfer (Poster)
Virat Shejwalkar
Unifying Privacy Loss for Data Analytics (Poster)
Ryan Rogers
Differentially Private Generative Models Through Optimal Transport (Poster)
Karsten Kreis
Challenges of Differentially Private Prediction in Healthcare Settings (Poster)
Nicolas Papernot
Privacy in Multi-armed Bandits: Fundamental Definitions and Lower Bounds on Regret (Poster)
Debabrota Basu
Privacy Risks in Embedded Deep Learning (Poster)
Virat Shejwalkar
CrypTen: Secure Multi-Party Computation Meets Machine Learning (Poster)
Shubho Sengupta
On the (Im)Possibility of Private Machine Learning through Instance Encoding (Oral)
Nicholas Carlini
Secure Single-Server Aggregation with (Poly)Logarithmic Overhead (Poster)
James Bell
Characterizing Private Clipped Gradient Descent on Convex Generalized Linear Problems (Poster)
Shuang Song
Local Differentially Private Regret Minimization in Reinforcement Learning (Poster)
Evrard Garcelon
Understanding Unintended Memorization in Federated Learning (Poster)
Om Thakkar
Dynamic Channel Pruning for Privacy (Poster)
Abhishek Singh
SOTERIA: In Search of Efficient Neural Networks for Private Inference (Poster)
Reza Shokri
Fairness in the Eyes of the Data: Certifying Machine-Learning Models (Poster)
Carsten Baum
Does Domain Generalization Provide Inherent Membership Privacy (Poster)
Divyat Mahajan
Enabling Fast Differentially Private SGD via Static Graph Compilation and Batch-Level Parallelism (Poster)
Pranav S Subramani
Shuffled Model of Federated Learning: Privacy, Accuracy, and Communication Trade-offs (Oral)
Deepesh Data
Poirot: Private Contact Summary Aggregation (Oral)
Chenghong Wang
Sample-efficient proper PAC learning with approximate differential privacy (Oral)
Badih Ghazi