HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption
Jul 24, 2023
Speakers
Seewoo Lee
Speaker · 0 followers
Jung Woo Kim
Speaker · 0 followers
Junbum Shin
Speaker · 0 followers
Mun-Kyu Lee
Speaker · 0 followers
About
Transfer learning is a de facto standard method for efficiently training machine learning models for data-scarce problems by adding and fine-tuning new classification layers to a model pre-trained on large datasets.Although numerous previous studies proposed to use homomorphic encryption to resolve the data privacy issue in transfer learning in the machine learning as a service setting,most of them only focused on encrypted inference. In this study, we present HETAL, an efficient Homomorphic Encryption based Transfer Learning algorithm, that protects the client's privacy in training tasks by encrypting the client data using the CKKS homomorphic encryption scheme.HETAL is the first practical scheme that strictly provides encrypted training, adopting validation-based early stopping and achieving the accuracy of nonencrypted training.We propose an efficient encrypted matrix multiplication algorithm, which is 1.8 to 323 times faster than prior methods, and a highly precise softmax approximation algorithm with increased coverage.The experimental results for five well-known benchmark datasets show total training times of 567–3442 seconds, which is less than an hour.Transfer learning is a de facto standard method for efficiently training machine learning models for data-scarce problems by adding and fine-tuning new classification layers to a model pre-trained on large datasets.Although numerous previous studies proposed to use homomorphic encryption to resolve the data privacy issue in transfer learning in the machine learning as a service setting,most of them only focused on encrypted inference. In this study, we present HETAL, an efficient Homomorphic Enc…
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
On the Convergence of SARSA with Linear Function Approximation
Watch later
On the Forward Invariance of Neural ODEs
Watch later
Wei Xiao, …
Self-Supervised Learning in Vision: from Research Advances to Best Practices
Watch later
Xinlei Chen, …
SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores
Watch later
Zhiyu Mei, …
