Low Latency Privacy Preserving Inference

Brutzkus, Alon; Elisha, Oren; Gilad-Bachrach, Ran

doi:10.48550/arxiv.1812.10659

Cited by 4 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…logistic regression [1,2,8,13,15], decision tree [11] and clustering [14,24]. As for the recent popularized deep models, there is effort on making inference over the private data [6,20,26], but not much on training. The major difficulty comes from the high complexity.…”

Section: Related Workmentioning

confidence: 99%

Faster Secure Data Mining via Distributed Homomorphic Encryption

Huang

2020

Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Due to the rising privacy demand in data mining, Homomorphic Encryption (HE) is receiving more and more attention recently for its capability to do computations over the encrypted field. By using the HE technique, it is possible to securely outsource model learning to the not fully trustful but powerful public cloud computing environments. However, HE-based training scales badly because of the high computation complexity. It is still an open problem whether it is possible to apply HE to large-scale problems. In this paper, we propose a novel general distributed HE-based data mining framework towards one step of solving the scaling problem. The main idea of our approach is to use the slightly more communication overhead in exchange of shallower computational circuit in HE, so as to reduce the overall complexity. We verify the efficiency and effectiveness of our new framework by testing over various data mining algorithms and benchmark data-sets. For example, we successfully train a logistic regression model to recognize the digit 3 and 8 within around 5 minutes, while a centralized counterpart needs almost 2 hours. CCS CONCEPTS• Security and privacy → Cryptography; Software and application security; Domain-specific security and privacy architectures.

show abstract

Section: Related Workmentioning

confidence: 99%

Faster Secure Data Mining via Distributed Homomorphic Encryption

Huang

2020

Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

show abstract

“…With the power of LHE, a two-party protocol is devised where interactions between the server and the client are minimized. However, due to the fact that HE parameters scale with the number of network layers, one of the most recent work [4] still requires more than 700 seconds to evaluate a relatively shallow neural network.…”

Section: Related Workmentioning

confidence: 99%

“…Recent advances in cryptographic primitives [14] and adversary models [19,21] have brought input-hiding SI into practical domain, where 32 × 32 image datasets can be classified within seconds [19,25]. Meanwhile, from a learning perspective, alternative feature representations are discussed to reduce the computational complexity of SI [4]. We also observe that hardware-friendly network architectures [8,9] can be adopted in a secure setting to reduce the computational and communicational overheads [25].…”

Section: Introductionmentioning

confidence: 99%

ENSEI: Efficient Secure Inference via Frequency-Domain Homomorphic Convolution for Privacy-Preserving Visual Recognition

Bian¹,

Wang²,

Hiromoto³

et al. 2020

Preprint

View full text Add to dashboard Cite

In this work, we propose ENSEI, a secure inference (SI) framework based on the frequency-domain secure convolution (FDSC) protocol for the efficient execution of privacypreserving visual recognition. Our observation is that, under the combination of homomorphic encryption and secret sharing, homomorphic convolution can be obliviously carried out in the frequency domain, significantly simplifying the related computations. We provide protocol designs and parameter derivations for number-theoretic transform (NTT) based FDSC. In the experiment, we thoroughly study the accuracy-efficiency trade-offs between time-and frequency-domain homomorphic convolution. With ENSEI, compared to the best known works, we achieve 5-11x online time reduction, up to 33x setup time reduction, and up to 10x reduction in the overall inference time. A further 33% of bandwidth reductions can be obtained on binary neural networks with only 1% of accuracy degradation on the CIFAR-10 dataset.

show abstract

Security and Privacy Issues in Deep Learning

Bae¹,

Jang²,

Jung³

et al. 2018

Preprint

View full text Add to dashboard Cite

With the development of machine learning, expectations for artificial intelligence (AI) technology are increasing day by day. In particular, deep learning has shown enriched performance results in a variety of fields. There are many applications that are closely related to our daily life, such as making significant decisions in application area based on predictions or classifications, in which a deep learning (DL) model could be relevant. Hence, if a DL model causes mispredictions or misclassifications due to malicious external influences, it can cause very large difficulties in real life. Moreover, training deep learning models involves relying on an enormous amount of data and the training data often includes sensitive information. Therefore, deep learning models should not expose the privacy of such data. In this paper, we reviewed the threats and developed defense methods on the security of the models and the data privacy under the notion of SPAI: Secure and Private AI. We also discuss current challenges and open issues.

show abstract

Low Latency Privacy Preserving Inference

Cited by 4 publications

References 20 publications

Faster Secure Data Mining via Distributed Homomorphic Encryption

Faster Secure Data Mining via Distributed Homomorphic Encryption

ENSEI: Efficient Secure Inference via Frequency-Domain Homomorphic Convolution for Privacy-Preserving Visual Recognition

Security and Privacy Issues in Deep Learning

Contact Info

Product

Resources

About