Differentially Private Deep Learning with Direct Feedback Alignment
Standard methods for differentially private training of deep neural networks replace back-propagated mini-batch gradients with biased and noisy approximations to the gradient. These modifications to training often result in a privacy-preserving model that is significantly less accurate than its non-private counterpart. We hypothesize that alternative training algorithms may be more amenable to differential privacy. Specifically, we examine the suitability of direct feedback alignment (DFA). We propose the first differentially private method for training deep neural networks with DFA and show that it achieves significant gains in accuracy (often by 10-20%) compared to backprop-based differentially private training on a variety of architectures (fully connected, convolutional) and datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep LearningPrivacy PreservingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Photonic Differential Privacy with Direct Feedback Alignment
Optical Processing Units (OPUs) -- low-power photonic chips dedicated to large scale random projections -- have been used in previous work to train deep neural networks using Direct Feedback Alignment (DFA), an effective…
Privacy-Preserving Reinforcement Learning from Human Feedback via Decoupled Reward Modeling
Preference-based fine-tuning has become an important component in training large language models, and the data used at this stage may contain sensitive user information. A central question is how to design a differential…
Reinforcement LearningDifferentially Private Linear Bandits with Partial Distributed Feedback
In this paper, we study the problem of global reward maximization with only partial distributed feedback. This problem is motivated by several real-world applications (e.g., cellular network configuration, dynamic pricin…
PROPS: Progressively Private Self-alignment of Large Language Models
Alignment is a key step in developing Large Language Models (LLMs) using human feedback to ensure adherence to human values and societal norms. Dependence on human feedback raises privacy concerns about how much a labele…
Locally Differentially Private (Contextual) Bandits Learning
We study locally differentially private (LDP) bandits learning in this paper. First, we propose simple black-box reduction frameworks that can solve a large family of context-free bandits learning problems with LDP guara…
Multi-Armed BanditsPrivacy Preserving Deep Learning