Quantum-secure multiparty deep learning
Secure multiparty computation enables the joint evaluation of multivariate functions across distributed users while ensuring the privacy of their local inputs. This field has become increasingly urgent due to the exploding demand for computationally intensive deep learning inference. These computations are typically offloaded to cloud computing servers, leading to vulnerabilities that can compromise the security of the clients' data. To solve this problem, we introduce a linear algebra engine that leverages the quantum nature of light for information-theoretically secure multiparty computation using only conventional telecommunication components. We apply this linear algebra engine to deep learning and derive rigorous upper bounds on the information leakage of both the deep neural network weights and the client's data via the Holevo and the Cram\'er-Rao bounds, respectively. Applied to the MNIST classification task, we obtain test accuracies exceeding $96\%$ while leaking less than $0.1$ bits per weight symbol and $0.01$ bits per data symbol. This weight leakage is an order of magnitude below the minimum bit precision required for accurate deep learning using state-of-the-art quantization techniques. Our work lays the foundation for practical quantum-secure computation and unlocks secure cloud deep learning as a field.
Code (0)
등록된 구현이 없습니다.
Tasks
Cloud ComputingDeep LearningQuantizationSimilar Papers 제목 키워드 기반
Federated Coordinate Descent for Privacy-Preserving Multiparty Linear Regression
Distributed privacy-preserving regression schemes have been developed and extended in various fields, where multiparty collaboratively and privately run optimization algorithms, e.g., Gradient Descent, to learn a set of …
Privacy PreservingregressionQuantum federated learning through blind quantum computing
Private distributed learning studies the problem of how multiple distributed entities collaboratively train a shared deep network with their private data unrevealed. With the security provided by the protocols of blind q…
BIG-bench Machine LearningFederated LearningSecure multiparty computations in floating-point arithmetic
Secure multiparty computations enable the distribution of so-called shares of sensitive data to multiple parties such that the multiple parties can effectively process the data while being unable to glean much informatio…
AllMathematical ProofsPrivacy PreservingregressionSecure multi-party linear regression at plaintext speed
We detail distributed algorithms for scalable, secure multiparty linear regression and feature selection at essentially the same speed as plaintext regression. While the core geometric ideas are simple, the recognition o…
feature selectionregressionTraining Differentially Private Models with Secure Multiparty Computation
We address the problem of learning a machine learning model from training data that originates at multiple data owners while providing formal privacy guarantees regarding the protection of each owner's data. Existing sol…
Privacy Preserving