( events)   Timezone: »  
Program Highlights »
Workshop
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)
Reza Shokri
Invited Talk #2: Katrina Ligett (Hebrew University) (Invited Talk)
Katrina Ligett
Invited Talk Q&A with Reza and Katrina (Q&A Session)
Break
Contributed Talk #1: POSEIDON: Privacy-Preserving Federated Neural Network Learning (Oral)
Sinem Sav
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)
Carmela Troncoso
Invited Talk #4: Dan Boneh (Stanford University) (Invited Talk)
Dan Boneh
Invited Talk Q&A with Carmela and Dan (Q&A Session)
Break
Poster Session & Social on Gather.Town (Poster Session)
Break
Contributed Talk #2: On the (Im)Possibility of Private Machine Learning through Instance Encoding (Oral)
Nicholas Carlini
Contributed Talk #3: Poirot: Private Contact Summary Aggregation (Oral)
Chenghong Wang
Contributed Talk #4: Greenwoods: A Practical Random Forest Framework for Privacy Preserving Training and Prediction (Oral)
Harsh Chaudhari
Contributed Talks Q&A (Q&A Session)
Break
Contributed Talk #5: Shuffled Model of Federated Learning: Privacy, Accuracy, and Communication Trade-offs (Oral)
Deepesh Data
Contributed Talk #6: Sample-efficient proper PAC learning with approximate differential privacy (Oral)
Badih Ghazi
Contributed Talk #7: Training Production Language Models without Memorizing User Data (Oral)
Swaroop Ramaswamy, Om Thakkar
Contributed Talks Q&A (Q&A Session)
Twinify: A software package for differentially private data release (Poster)
Joonas Jälkö
SparkFHE: Distributed Dataflow Framework with Fully Homomorphic Encryption (Poster)
Peizhao Hu
DAMS: Meta-estimation of private sketch data structures for differentially private contact tracing (Poster)
Praneeth Vepakomma
Multi-Headed Global Model for handling Non-IID data (Poster)
Himanshu Arora
Mitigating Leakage in Federated Learning with Trusted Hardware (Poster)
Javad Ghareh Chamani
Robustness Threats of Differential Privacy (Poster)
Ivan Oseledets
Accuracy, Interpretability and Differential Privacy via Explainable Boosting (Poster)
Harsha Nori
Asymmetric Private Set Intersection with Applications to Contact Tracing and Private Vertical Federated Machine Learning (Poster)
Bogdan Cebere
Adversarial Attacks and Countermeasures on Private Training in MPC (Poster)
Matthew Jagielski
Unifying Privacy Loss for Data Analytics (Poster)
Ryan Rogers
Machine Learning with Membership Privacy via Knowledge Transfer (Poster)
Virat Shejwalkar
Dynamic Channel Pruning for Privacy (Poster)
Abhishek Singh
Privacy Risks in Embedded Deep Learning (Poster)
Virat Shejwalkar
Robust and Private Learning of Halfspaces (Poster)
Badih Ghazi
Challenges of Differentially Private Prediction in Healthcare Settings (Poster)
Nicolas Papernot
Privacy Preserving Chatbot Conversations (Poster)
Debmalya Biswas
Secure Single-Server Aggregation with (Poly)Logarithmic Overhead (Poster)
James Bell
Generative Adversarial User Privacy in Lossy Single-Server Information Retrieval (Poster)
Mark Weng
Revisiting Membership Inference Under Realistic Assumptions (Poster)
Bargav Jayaraman
Quantifying Privacy Leakage in Graph Embedding (Poster)
Antoine Boutet
Understanding Unintended Memorization in Federated Learning (Poster)
Om Thakkar
Effectiveness of MPC-friendly Softmax Replacement (Poster)
Marcel Keller
Differentially private cross-silo federated learning (Poster)
Mikko Heikkilä
Differentially Private Stochastic Coordinate Descent (Poster)
Georgios Damaskinos
Does Domain Generalization Provide Inherent Membership Privacy (Poster)
Divyat Mahajan
CrypTen: Secure Multi-Party Computation Meets Machine Learning (Poster)
Shubho Sengupta
On Polynomial Approximations for Privacy-Preserving and Verifiable ReLU Networks (Poster)
Salman Avestimehr
Data-oblivious training for XGBoost models (Poster)
Chester Leung
Dataset Inference: Ownership Resolution in Machine Learning (Poster)
Nicolas Papernot
Distributed Differentially Private Averaging with Improved Utility and Robustness to Malicious Parties (Poster)
Aurélien Bellet
Secure Medical Image Analysis with CrypTFlow (Poster)
Javier Alvarez-Valle
Differentially Private Generative Models Through Optimal Transport (Poster)
Karsten Kreis
Privacy Regularization: Joint Privacy-Utility Optimization in Language Models (Poster)
FatemehSadat Mireshghallah
On the Sample Complexity of Privately Learning Unbounded High-Dimensional Gaussians (Poster)
Ishaq Aden-Ali
SOTERIA: In Search of Efficient Neural Networks for Private Inference (Poster)
Reza Shokri
Network Generation with Differential Privacy (Poster)
Xu Zheng
Randomness Beyond Noise: Differentially Private Optimization Improvement through Mixup (Poster)
Hanshen Xiao
Characterizing Private Clipped Gradient Descent on Convex Generalized Linear Problems (Poster)
Shuang Song
PrivAttack: A Membership Inference AttackFramework Against Deep Reinforcement LearningAgents (Poster)
maziar gomrokchi
SWIFT: Super-fast and Robust Privacy-Preserving Machine Learning (Poster)
Nishat Koti
DYSAN: Dynamically sanitizing motion sensor data against sensitive inferences through adversarial networks (Poster)
Théo JOURDAN
Differentially Private Bayesian Inference For GLMs (Poster)
Joonas Jälkö
MP2ML: A Mixed-Protocol Machine LearningFramework for Private Inference (Poster)
Fabian Boemer
Data Appraisal Without Data Sharing (Poster)
Mimee Xu
Enabling Fast Differentially Private SGD via Static Graph Compilation and Batch-Level Parallelism (Poster)
Pranav Subramani
Privacy-preserving XGBoost Inference (Poster)
Xianrui Meng
New Challenges for Fully Homomorphic Encryption (Poster)
Marc Joye
Local Differentially Private Regret Minimization in Reinforcement Learning (Poster)
Evrard Garcelon
Individual Privacy Accounting via a Rényi Filter (Poster)
Vitaly Feldman
Privacy Attacks on Machine Unlearning (Poster)
Ji Gao
Privacy in Multi-armed Bandits: Fundamental Definitions and Lower Bounds on Regret (Poster)
Debabrota Basu
A Principled Approach to Learning Stochastic Representations for Privacy in Deep Neural Inference (Poster)
FatemehSadat Mireshghallah
Towards General-purpose Infrastructure for Protecting Scientific Data Under Study (Poster)
Kritika Prakash
Optimal Client Sampling for Federated Learning (Poster)
Samuel Horváth
Privacy Amplification by Decentralization (Poster)
Aurélien Bellet
Fairness in the Eyes of the Data: Certifying Machine-Learning Models (Poster)
Carsten Baum
Tight Approximate Differential Privacy for Discrete-Valued Mechanisms Using FFT (Poster)
Antti Koskela
Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling (Poster)
Vitaly Feldman