Helen: Maliciously Secure Coopetitive Learning for Linear Models
arXiv:1907.07212
Abstract
Many organizations wish to collaboratively train machine learning models on their combined datasets for a common benefit (e.g., better medical research, or fraud detection). However, they often cannot share their plaintext datasets due to privacy concerns and/or business competition. In this paper, we design and build Helen, a system that allows multiple parties to train a linear model without revealing their data, a setting we call coopetitive learning. Compared to prior secure training systems, Helen protects against a much stronger adversary who is malicious and can compromise m-1 out of m parties. Our evaluation shows that Helen can achieve up to five orders of magnitude of performance improvement when compared to training using an existing state-of-the-art secure multi-party computation framework.
References in corpus (10)
- Deep Learning with Differential Privacy
- Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
- The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks
- Inferring Fine-grained Control Flow Inside SGX Enclaves with Branch Shadowing
- A Berkeley View of Systems Challenges for AI
- Gazelle: A Low Latency Framework for Secure Neural Network Inference
- Prio: Private, Robust, and Scalable Computation of Aggregate Statistics
- Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning
- Local Privacy, Data Processing Inequalities, and Statistical Minimax Rates
- Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks