Oblivious Neural Network Predictions via MiniONN Transformations

By Jian Liu, Mika Juuti, N. Asokan. 2017

809 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Privacy & Security

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Privacy & Security

Citations in the corpus

Privacy in Deep Learning: A Survey (2020, methodology): “propose MiniONN [116], which uses additively homomorphic encryption (AHE) in a preprocessing step, unlike GAZELLE which uses AHE to speed up linear algebra directly.”
Secure Evaluation of Quantized Neural Networks (2019, methodology): “The first of these is MiniONN [48] which provides techniques for converting existing models into models that can be evaluated securely.”
Federated Machine Learning (2019, background): “With the recent advances in deep learning, privacy-preserving neural networks inference is also receiving a lot of research interest [10, 11, 14, 28, 40, 52, 54].”
Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware (2018, background): “, in the latter two where the computation is performed locally by the data owner), the need for integrity is a common denominator, and this is the property we primarily focus on in this paper (and for which we obtain the best results!) Cryptography can address some of these problems [17, 32, 3, 38, ”
DeepSecure: Scalable Provably-Secure Deep Learning (2017, methodology): “The MiniONN framework [26] is also based on additive secret-sharing and GC but has lower latency compared to SecureML approach.”
Gazelle: A Low Latency Framework for Secure Neural Network Inference (2018, methodology): “However even for these the network our efﬁcient FC and Conv implementation allows us roughly 30 × and 17 × lower runtime when compared with [29] and [26] respectively.”
Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications (2018, methodology): “MiniONN also supports non-linear activation functions and max-pooling.”
Blind Justice: Fairness with Encrypted Sensitive Attributes (2018, background): “…regression (Nikolaenko et al., 2013b; Gasc´on et al., 2017; Mohassel & Zhang, 2017), neural network training (Mohassel & Zhang, 2017) and evaluation (Juvekar et al., 2018; Liu et al., 2017), matrix factorization (Nikolaenko et al., 2013a), and principal component analysis (Al-Rubaie et al., 2017).”
Cheetah: Optimizing and Accelerating Homomorphic Encryption for Private Inference (2020, methodology): “2: Overview of how data is processed using BFV homomorphic encryption. execute linear operators (FC/CNNs) on the cloud using either homomorphic encryption (Gazelle [33]) or secret-sharing (MiniONN [37]), and non-linear functions on the client with Yao’s garbled circuit (GC).”
SecureNN: Efficient and Private Neural Network Training (2018, methodology): “All of the previous schemes [31, 30, 35, 27] use expensive garbled circuits for activations.”
Efficient Multi-Key Homomorphic Encryption with Packed Ciphertexts with Application to Oblivious Neural Network Inference (2019, neutral): “In Table 6, we compare our benchmark result with the state-of-the-art frameworks for oblivious neural network inference: CryptoNets [29], MiniONN [42], Gazelle [35], and E2DM [34].”
TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service (2018, methodology): “It is important to distinguish between approaches purely based on homomorphic encryption (described above), and those involving MultiParty Computation (MPC) techniques, such as (Mohassel & Zhang, 2017; Liu et al., 2017; Rouhani et al., 2017; Riazi et al., 2017; Chase et al.; Juvekar et al., 2018).”
Towards Deep Neural Network Training on Encrypted Data (2019, methodology): “Many more interactive protocols for the inference phase were suggested recently, including SecureML of Mohassel and Zhang [23], MiniONN of Liu et al. [22], Chameleon of Riazi et al. [26], and GAZEELE of Juvekar et al. [28].”
Privacy-Preserving Inference in Machine Learning Services Using Trusted Execution Environments (2019, background): “One approach to protect confidentiality of data is using cryptographic deep learning models [11], [23].”
A Survey of Privacy Attacks in Machine Learning (2020, neutral): “CelebA [54] images binary classification [11, 21, 104, 109] 20-202,599”
CrypTFlow2: Practical 2-Party Secure Inference (2020, methodology): “Finally, by picking 𝑚 appropriately, we obtain a protocol for millionaires’ whose concrete communication (in bits) is nearly 5 times better than prior work.”