Privacy Preserving Deep Learning
26 papers with code • 0 benchmarks • 3 datasets
The goal of privacy-preserving (deep) learning is to train a model while preserving privacy of the training dataset. Typically, it is understood that the trained model should be privacy-preserving (e.g., due to the training algorithm being differentially private).
Benchmarks
These leaderboards are used to track progress in Privacy Preserving Deep Learning
PA-HMDB51
ConcurrentQA Benchmark
Most implemented papers
Secure Data Sharing With Flow Model
In the classical multi-party computation setting, multiple parties jointly compute a function without revealing their own input data.
Can we Generalize and Distribute Private Representation Learning?
We study the problem of learning representations that are private yet informative, i. e., provide information about intended "ally" targets while hiding sensitive "adversary" attributes.
Practical Privacy Filters and Odometers with Rényi Differential Privacy and Applications to Differentially Private Deep Learning
Differential Privacy (DP) is the leading approach to privacy preserving deep learning.
CryptGPU: Fast Privacy-Preserving Machine Learning on the GPU
We then identify a sequence of "GPU-friendly" cryptographic protocols to enable privacy-preserving evaluation of both linear and non-linear operations on the GPU.
Variational Leakage: The Role of Information Complexity in Privacy Leakage
BehroozRazeghi/Variational-Leakage
•
•
We study the role of information complexity in privacy leakage about an attribute of an adversary's interest, which is not known a priori to the system designer.
Antipodes of Label Differential Privacy: PATE and ALIBI
facebookresearch/label_dp_antipodes
•
•
NeurIPS 2021
We propose two novel approaches based on, respectively, the Laplace mechanism and the PATE framework, and demonstrate their effectiveness on standard benchmarks.
Towards Secure and Practical Machine Learning via Secret Sharing and Random Permutation
zfscgy/Amber
•
•
Since our method reduces the cost for element-wise function computation, it is more efficient than existing cryptographic methods.
Homogeneous Learning: Self-Attention Decentralized Deep Learning
yuweisunn/homogeneous-learning
•
•
To this end, we propose a decentralized learning model called Homogeneous Learning (HL) for tackling non-IID data with a self-attention mechanism.
Backpropagation Clipping for Deep Learning with Differential Privacy
uvm-plaid/backpropagation-clipping
•
•
We present backpropagation clipping, a novel variant of differentially private stochastic gradient descent (DP-SGD) for privacy-preserving deep learning.
Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility
In this work, we propose a general family of optimization problems, termed as complexity-leakage-utility bottleneck (CLUB) model, which (i) provides a unified theoretical framework that generalizes most of the state-of-the-art literature for the information-theoretic privacy models, (ii) establishes a new interpretation of the popular generative and discriminative models, (iii) constructs new insights to the generative compression models, and (iv) can be used in the fair generative models.
