Timezone: »

 
Workshop
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

Fri Dec 11 12:00 AM -- 09:25 AM (PST) @ None
Event URL: https://ppml-workshop.github.io/ »

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.

Fri 12:00 a.m. - 12:40 a.m.
Invited talk #1: Reza Shokri (National University of Singapore) (Talk)
Reza Shokri
Fri 2:40 a.m. - 3:20 a.m.
Invited talk #2: Carmela Troncoso (EPFL) (Talk)
Carmela Troncoso
Fri 8:00 a.m. - 8:40 a.m.
Invited talk #3: Katrina Ligett (Hebrew University) (Talk)
Katrina Ligett
Fri 8:45 a.m. - 9:25 a.m.
Invited talk #4: Dan Boneh (Stanford University) (Talk)
Dan Boneh
-
Shuffled Model of Federated Learning: Privacy, Accuracy, and Communication Trade-offs (Oral)
Deepesh Data
-
Poirot: Private Contact Summary Aggregation (Oral)
Chenghong Wang
-
On the (Im)Possibility of Private Machine Learning through Instance Encoding (Oral)
Nicholas Carlini
-
POSEIDON: Privacy-Preserving Federated Neural Network Learning (Oral)
Sinem Sav
-
Sample-efficient proper PAC learning with approximate differential privacy (Oral)
Badih Ghazi
-
Training Production Language Models without Memorizing User Data (Oral)
Swaroop Ramaswamy
-
Greenwoods: A Practical Random Forest Framework for Privacy Preserving Training and Prediction (Oral)
Harsh Chaudhari
-
Towards General-purpose Infrastructure for Protecting Scientific Data Under Study (Poster) [ Video ]
Kritika Prakash
-
Robust and Private Learning of Halfspaces (Poster) [ Video ]
Badih Ghazi
-
Randomness Beyond Noise: Differentially Private Optimization Improvement through Mixup (Poster) [ Video ]
Hanshen Xiao
-
Generative Adversarial User Privacy in Lossy Single-Server Information Retrieval (Poster) [ Video ]
Mark Weng
-
Privacy Preserving Chatbot Conversations (Poster) [ Video ]
Debmalya Biswas
-
Distributed Differentially Private Averaging with Improved Utility and Robustness to Malicious Parties (Poster) [ Video ]
Aurélien Bellet
-
Twinify: A software package for differentially private data release (Poster) [ Video ]
Joonas Jälkö
-
DAMS: Meta-estimation of private sketch data structures for differentially private contact tracing (Poster) [ Video ]
Praneeth Vepakomma
-
Secure Medical Image Analysis with CrypTFlow (Poster) [ Video ]
Javier Alvarez-Valle
-
Multi-Headed Global Model for handling Non-IID data (Poster) [ Video ]
Himanshu Arora
-
Individual Privacy Accounting via a Rényi Filter (Poster) [ Video ]
Vitaly Feldman
-
Does Domain Generalization Provide Inherent Membership Privacy (Poster) [ Video ]
Divyat Mahajan
-
Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling (Poster) [ Video ]
Vitaly Feldman
-
SparkFHE: Distributed Dataflow Framework with Fully Homomorphic Encryption (Poster) [ Video ]
Peizhao Hu
-
Enabling Fast Differentially Private SGD via Static Graph Compilation and Batch-Level Parallelism (Poster) [ Video ]
Pranav S Subramani
-
Local Differentially Private Regret Minimization in Reinforcement Learning (Poster) [ Video ]
Evrard Garcelon
-
SWIFT: Super-fast and Robust Privacy-Preserving Machine Learning (Poster) [ Video ]
Nishat Koti
-
Differentially Private Stochastic Coordinate Descent (Poster) [ Video ]
Celestine Mendler-Dünner
-
MP2ML: A Mixed-Protocol Machine LearningFramework for Private Inference (Poster) [ Video ]
Fabian Boemer
-
Dataset Inference: Ownership Resolution in Machine Learning (Poster) [ Video ]
Nicolas Papernot
-
Privacy-preserving XGBoost Inference (Poster) [ Video ]
Xianrui Meng
-
New Challenges for Fully Homomorphic Encryption (Poster) [ Video ]
Marc Joye
-
Differentially Private Bayesian Inference For GLMs (Poster) [ Video ]
Joonas Jälkö
-
Robustness Threats of Differential Privacy (Poster) [ Video ]
Ivan Oseledets
-
Asymmetric Private Set Intersection with Applications to Contact Tracing and Private Vertical Federated Machine Learning (Poster) [ Video ]
Bogdan Cebere
-
Characterizing Private Clipped Gradient Descent on Convex Generalized Linear Problems (Poster) [ Video ]
Shuang Song
-
Adversarial Attacks and Countermeasures on Private Training in MPC (Poster) [ Video ]
Matthew Jagielski
-
Optimal Client Sampling for Federated Learning (Poster) [ Video ]
Samuel Horváth
-
Data Appraisal Without Data Sharing (Poster) [ Video ]
Mimee Xu
-
Dynamic Channel Pruning for Privacy (Poster) [ Video ]
Abhishek Singh
-
Mitigating Leakage in Federated Learning with Trusted Hardware (Poster) [ Video ]
Javad Ghareh Chamani
-
Unifying Privacy Loss for Data Analytics (Poster) [ Video ]
Ryan Rogers
-
Differentially Private Generative Models Through Optimal Transport (Poster) [ Video ]
Karsten Kreis
-
A Principled Approach to Learning Stochastic Representations for Privacy in Deep Neural Inference (Poster) [ Video ]
FatemehSadat Mireshghallah
-
Challenges of Differentially Private Prediction in Healthcare Settings (Poster) [ Video ]
Nicolas Papernot
-
Machine Learning with Membership Privacy via Knowledge Transfer (Poster) [ Video ]
Virat Shejwalkar
-
Secure Single-Server Aggregation with (Poly)Logarithmic Overhead (Poster) [ Video ]
James Bell
-
PrivAttack: A Membership Inference AttackFramework Against Deep Reinforcement LearningAgents (Poster) [ Video ]
maziar gomrokchi
-
Effectiveness of MPC-friendly Softmax Replacement (Poster) [ Video ]
Marcel Keller
-
Revisiting Membership Inference Under Realistic Assumptions (Poster) [ Video ]
Bargav Jayaraman
-
DYSAN: Dynamically sanitizing motion sensor data against sensitive inferences through adversarial networks (Poster) [ Video ]
Théo JOURDAN
-
Fairness in the Eyes of the Data: Certifying Machine-Learning Models (Poster) [ Video ]
Carsten Baum
-
Privacy in Multi-armed Bandits: Fundamental Definitions and Lower Bounds on Regret (Poster) [ Video ]
Debabrota Basu
-
Accuracy, Interpretability and Differential Privacy via Explainable Boosting (Poster) [ Video ]
Harsha Nori
-
Privacy Amplification by Decentralization (Poster) [ Video ]
Aurélien Bellet
-
Privacy Risks in Embedded Deep Learning (Poster) [ Video ]
Virat Shejwalkar
-
Quantifying Privacy Leakage in Graph Embedding (Poster) [ Video ]
Antoine Boutet
-
Understanding Unintended Memorization in Federated Learning (Poster) [ Video ]
Om Thakkar
-
Network Generation with Differential Privacy (Poster) [ Video ]
Xu Zheng
-
Privacy Regularization: Joint Privacy-UtilityOptimization in Language Models (Poster) [ Video ]
FatemehSadat Mireshghallah
-
Tight Approximate Differential Privacy for Discrete-Valued Mechanisms Using FFT (Poster) [ Video ]
Antti Koskela
-
Differentially private cross-silo federated learning (Poster) [ Video ]
Mikko Heikkilä
-
CrypTen: Secure Multi-Party Computation Meets Machine Learning (Poster) [ Video ]
Shubho Sengupta
-
On Polynomial Approximations for Privacy-Preserving and Verifiable ReLU Networks (Poster) [ Video ]
Salman Avestimehr
-
Data-oblivious training for XGBoost models (Poster) [ Video ]
Chester Leung
-
Privacy Attacks on Machine Unlearning (Poster) [ Video ]
Ji Gao
-
SOTERIA: In Search of Efficient Neural Networks for Private Inference (Poster) [ Video ]
Reza Shokri
-
On the Sample Complexity of Privately Learning Unbounded High-Dimensional Gaussians (Poster) [ Video ]
Ishaq Aden-Ali

Author Information

Borja Balle (DeepMind)
James Bell (Alan Turing Institute)
Aurélien Bellet (INRIA)
Kamalika Chaudhuri (UCSD)
Adria Gascon (Alan Turing Institute and Warwick university)
Antti Honkela (University of Helsinki)
Antti Koskela (University of Helsinki)
Casey Meehan (University of California, San Diego)
Olga Ohrimenko (The University of Melbourne)
Mi Jung Park (MPI-IS Tuebingen)
Mariana Raykova (Google)
Mary Anne Smart (University of California, San Diego)
Yu-Xiang Wang (UC Santa Barbara)
Adrian Weller (Cambridge, Alan Turing Institute)

Adrian Weller is Programme Director for AI at The Alan Turing Institute, the UK national institute for data science and AI, where he is also a Turing Fellow leading work on safe and ethical AI. He is a Senior Research Fellow in Machine Learning at the University of Cambridge, and at the Leverhulme Centre for the Future of Intelligence where he leads the project on Trust and Transparency. His interests span AI, its commercial applications and helping to ensure beneficial outcomes for society. He serves on several boards including the Centre for Data Ethics and Innovation. Previously, Adrian held senior roles in finance.

More from the Same Authors