Oblivious Neural Network Predictions via MiniONN Transformations

Liu, Jian; Juuti, Mika; Lu, Yao; Asokan, N.

doi:10.1145/3133956.3134056

Cited by 548 publications

(515 citation statements)

References 29 publications

Supporting

Mentioning

512

Contrasting

Unclassified

Order By: Relevance

“…The final polynomial objective function used for training is given in Eq. (17). Lemma 4: Let S and S be any two neighboring databases.…”

Section: Secprobe: the Participant Partmentioning

confidence: 99%

“…In [16], homomorphic encryption was first applied to convolutional neural networks (CNNs), where the model was trained in a centralized manner, and it required extensive computation resources. Subsequently, many other works tried arXiv:1812.10113v3 [cs.CR] 25 Oct 2019 to make inferences on encrypted data, e.g., [17]- [21], etc. However, although the recent schemes have improved the efficiency significantly, they often lead to much higher overheads as compared to computing on the original plaintext data.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Privacy-Preserving Collaborative Deep Learning With Unreliable Participants

Zhao

Wang

Zou

et al. 2020

IEEE Trans.Inform.Forensic Secur.

170

View full text Add to dashboard Cite

With powerful parallel computing GPUs and massive user data, neural-network-based deep learning can well exert its strong power in problem modeling and solving, and has archived great success in many applications such as image classification, speech recognition and machine translation etc. While deep learning has been increasingly popular, the problem of privacy leakage becomes more and more urgent. Given the fact that the training data may contain highly sensitive information, e.g., personal medical records, directly sharing them among the users (i.e., participants) or centrally storing them in one single location may pose a considerable threat to user privacy.In this paper, we present a practical privacy-preserving collaborative deep learning system that allows users to cooperatively build a collective deep learning model with data of all participants, without direct data sharing and central data storage. In our system, each participant trains a local model with their own data and only shares model parameters with the others. To further avoid potential privacy leakage from sharing model parameters, we use functional mechanism to perturb the objective function of the neural network in the training process to achieve -differential privacy. In particular, for the first time, we consider the existence of unreliable participants, i.e., the participants with low-quality data, and propose a solution to reduce the impact of these participants while protecting their privacy. We evaluate the performance of our system on two well-known real-world datasets for regression and classification tasks. The results demonstrate that the proposed system is robust against unreliable participants, and achieves high accuracy close to the model trained in a traditional centralized manner while ensuring rigorous privacy protection.

show abstract

“…The final polynomial objective function used for training is given in Eq. (17). Lemma 4: Let S and S be any two neighboring databases.…”

Section: Secprobe: the Participant Partmentioning

confidence: 99%

mentioning

confidence: 99%

Privacy-Preserving Collaborative Deep Learning With Unreliable Participants

Zhao

Wang

Zou

et al. 2020

IEEE Trans.Inform.Forensic Secur.

170

View full text Add to dashboard Cite

show abstract

“…Finally, we assume the use of secure channel, which can be instantiated by the transport layer security (TLS) [28]. This setting is the same as that in other literature [5], [15].…”

Section: Security and Network Settingsmentioning

confidence: 99%

MOBIUS: Model-Oblivious Binarized Neural Networks

et al. 2019

View full text Add to dashboard Cite

A privacy-preserving framework in which a computational resource provider receives encrypted data from a client and returns prediction results without decrypting the data, i.e., oblivious neural network or encrypted prediction, has been studied in machine learning that provides prediction services. In this work, we present MOBIUS (Model-Oblivious BInary neUral networkS), a new system that combines Binarized Neural Networks (BNNs) and secure computation based on secret sharing as tools for scalable and fast privacy-preserving machine learning. BNNs improve computational performance by binarizing values in training to −1 and +1, while secure computation based on secret sharing provides fast and various computations under encrypted forms via modulo operations with a short bit length. However, combining these tools is not trivial because their operations have different algebraic structures and the use of BNNs downgrades prediction accuracy in general. MOBIUS uses improved procedures of BNNs and secure computation that have compatible algebraic structures without downgrading prediction accuracy. We created an implementation of MOBIUS in C++ using the ABY library (NDSS 2015). We then conducted experiments using the MNIST dataset, and the results show that MOBIUS can return a prediction within 0.76 seconds, which is six times faster than SecureML (IEEE S&P 2017). MOBIUS allows a client to request for encrypted prediction and allows a trainer to obliviously publish an encrypted model to a cloud provided by a computational resource provider, i.e., without revealing the original model itself to the provider.

show abstract

“…Processing on Encrypted Data At processing phase, SMC has led to cooperative solutions where several devices work together to obtain federated inferences [Liu et al, 2017], not supporting deployment of the trained DNN to trusted decentralized systems. DNN processing on FHE encrypted data is covered in CryptoNets [Gilad-Bachrach et al, 2016] More recently, in [Boemer et al, 2018], the authors proposed a privacy-preserving framework for deep learning, making use of the SEAL [SEAL, 2018] FHE library.…”

Section: Problem Statementmentioning

confidence: 99%

Security for Distributed Deep Neural Networks: Towards Data Confidentiality & Intellectual Property Protection

Gomez¹,

Wilhelm

Andújar

et al. 2019

Proceedings of the 16th International Joint Conference on E-Business and Telecommunications

View full text Add to dashboard Cite

Current developments in Enterprise Systems observe a paradigm shift, moving the needle from the backend to the edge sectors of those; by distributing data, decentralizing applications and integrating novel components seamlessly to the central systems. Distributively deployed AI capabilities will thrust this transition. Several non-functional requirements arise along with these developments, security being at the center of the discussions. Bearing those requirements in mind, hereby we propose an approach to holistically protect distributed Deep Neural Network (DNN) based/enhanced software assets, i.e. confidentiality of their input & output data streams as well as safeguarding their Intellectual Property. Making use of Fully Homomorphic Encryption (FHE), our approach enables the protection of Distributed Neural Networks, while processing encrypted data. On that respect we evaluate the feasibility of this solution on a Convolutional Neuronal Network (CNN) for image classification deployed on distributed infrastructures.

show abstract

Oblivious Neural Network Predictions via MiniONN Transformations

Cited by 548 publications

References 29 publications

Privacy-Preserving Collaborative Deep Learning With Unreliable Participants

Privacy-Preserving Collaborative Deep Learning With Unreliable Participants

MOBIUS: Model-Oblivious Binarized Neural Networks

Security for Distributed Deep Neural Networks: Towards Data Confidentiality & Intellectual Property Protection

Contact Info

Product

Resources

About