اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدHEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture
99
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Recently Homomorphic Encryption (HE) is used to implement Privacy-Preserving Neural Networks (PPNNs) that perform inferences directly on encrypted data without decryption. Prior PPNNs adopt mobile network architectures such as SqueezeNet for smaller computing overhead, but we find naively using mobile network architectures for a PPNN does not necessarily achieve shorter inference latency. Despite having less parameters, a mobile network architecture typically introduces more layers and increases the HE multiplicative depth of a PPNN, thereby prolonging its inference latency. In this paper, we propose a textbf{HE}-friendly privacy-preserving textbf{M}obile neural ntextbf{ET}work architecture, textbf{HEMET}. Experimental results show that, compared to state-of-the-art (SOTA) PPNNs, HEMET reduces the inference latency by $59.3%sim 61.2%$, and improves the inference accuracy by $0.4 % sim 0.5%$.
قيم البحث
اقرأ أيضاً
Set-based estimation has gained a lot of attention due to its ability to guarantee state enclosures for safety-critical systems. However, it requires computationally expensive operations, which in turn often requires outsourcing of these operations t
o cloud-computing platforms. Consequently, this raises some concerns with regard to sharing sensitive information and measurements. This paper presents the first privacy-preserving set-based estimation protocols using partially homomorphic encryption in which we preserve the privacy of the set of all possible estimates and the measurements. We consider a linear discrete-time dynamical system with bounded modeling and measurement uncertainties without any other statistical assumptions. We represent sets by zonotopes and constrained zonotopes as they can compactly represent high-dimensional sets and are closed under linear maps and Minkowski addition. By selectively encrypting some parameters of the used set representations, we are able to intersect sets in the encrypted domain, which enables guaranteed state estimation while ensuring the privacy goals. In particular, we show that our protocols achieve computational privacy using formal cryptographic definitions of computational indistinguishability. We demonstrate the efficiency of our approach by localizing a mobile quadcopter using custom ultra-wideband wireless devices. Our code and data are available online.
Distribution grid agents are obliged to exchange and disclose their states explicitly to neighboring regions to enable distributed optimal power flow dispatch. However, the states contain sensitive information of individual agents, such as voltage an
d current measurements. These measurements can be inferred by adversaries, such as other participating agents or eavesdroppers. To address the issue, we propose a privacy-preserving distributed optimal power flow (OPF) algorithm based on partially homomorphic encryption (PHE). First of all, we exploit the alternating direction method of multipliers (ADMM) to solve the OPF in a distributed fashion. In this way, the dual update of ADMM can be encrypted by PHE. We further relax the augmented term of the primal update of ADMM with the $ell_1$-norm regularization. In addition, we transform the relaxed ADMM with the $ell_1$-norm regularization to a semidefinite program (SDP), and prove that this transformation is exact. The SDP can be solved locally with only the sign messages from neighboring agents, which preserves the privacy of the primal update. At last, we strictly prove the privacy preservation guarantee of the proposed algorithm. Numerical case studies validate the effectiveness and exactness of the proposed approach.
In this paper, we address the problem of privacy-preserving training and evaluation of neural networks in an $N$-party, federated learning setting. We propose a novel system, POSEIDON, the first of its kind in the regime of privacy-preserving neural
network training. It employs multiparty lattice-based cryptography to preserve the confidentiality of the training data, the model, and the evaluation data, under a passive-adversary model and collusions between up to $N-1$ parties. To efficiently execute the secure backpropagation algorithm for training neural networks, we provide a generic packing approach that enables Single Instruction, Multiple Data (SIMD) operations on encrypted data. We also introduce arbitrary linear transformations within the cryptographic bootstrapping operation, optimizing the costly cryptographic computations over the parties, and we define a constrained optimization problem for choosing the cryptographic parameters. Our experimental results show that POSEIDON achieves accuracy similar to centralized or decentralized non-private approaches and that its computation and communication overhead scales linearly with the number of parties. POSEIDON trains a 3-layer neural network on the MNIST dataset with 784 features and 60K samples distributed among 10 parties in less than 2 hours.
We introduce S++, a simple, robust, and deployable framework for training a neural network (NN) using private data from multiple sources, using secret-shared secure function evaluation. In short, consider a virtual third party to whom every data-hold
er sends their inputs, and which computes the neural network: in our case, this virtual third party is actually a set of servers which individually learn nothing, even with a malicious (but non-colluding) adversary. Previous work in this area has been limited to just one specific activation function: ReLU, rendering the approach impractical for many use-cases. For the first time, we provide fast and verifiable protocols for all common activation functions and optimize them for running in a secret-shared manner. The ability to quickly, verifiably, and robustly compute exponentiation, softmax, sigmoid, etc., allows us to use previously written NNs without modification, vastly reducing developer effort and complexity of code. In recent times, ReLU has been found to converge much faster and be more computationally efficient as compared to non-linear functions like sigmoid or tanh. However, we argue that it would be remiss not to extend the mechanism to non-linear functions such as the logistic sigmoid, tanh, and softmax that are fundamental due to their ability to express outputs as probabilities and their universal approximation property. Their contribution in RNNs and a few recent advancements also makes them more relevant.
Recently, Lu et al. have proposed two image search schemes based on additive homomorphic encryption [IEEE Access, 2 (2014), 125-141]. We remark that both two schemes are flawed because: (1) the first scheme does not make use of the additive homomorph
ic property at all; (2) the additive homomorphic encryption in the second scheme is unnecessary and can be replaced by a more efficient symmetric key encryption.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
