nGraph-HE: A Graph Compiler for Deep Learning on Homomorphically Encrypted Data

Boemer, Fabian; Lao, Yixing; Cammarota, Rosario; Wierzynski, Casimir

doi:10.48550/arxiv.1810.10121

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, privacy-aware or privacy-preserving AI notion and several studies along this paradigm has been conducted, leading to influential concepts including federated learning and differential privacy [92,93]. With the use of homomorphic encryption, deep learning model inference on encrypted data was shown to be possible with a little trade-off from accuracy as well [94,95]. In addition, Shokri et al introduced and elaborated on the concept called membership inference attack, i.e., given a black-box machine learning model and a data record, determining whether this record was used as part of the model's training dataset or not [96].…”

Section: Privacy-aware Aimentioning

confidence: 99%

HARK Side of Deep Learning -- From Grad Student Descent to Automated Machine Learning

Gencoglu¹,

Gils²,

Guldogan³

et al. 2019

Preprint

View full text Add to dashboard Cite

Recent advancements in machine learning research, i.e., deep learning, introduced methods that excel conventional algorithms as well as humans in several complex tasks, ranging from detection of objects in images and speech recognition to playing difficult strategic games. However, the current methodology of machine learning research and consequently, implementations of the real-world applications of such algorithms, seems to have a recurring HARKing (Hypothesizing After the Results are Known) issue. In this work, we elaborate on the algorithmic, economic and social reasons and consequences of this phenomenon. We present examples from current common practices of conducting machine learning research (e.g., avoidance of reporting negative results) and failure of generalization ability of the proposed algorithms and datasets in actual real-life usage. Furthermore, a potential future trajectory of machine learning research and development from the perspective of accountable, unbiased, ethical and privacy-aware algorithmic decision making is discussed. We would like to emphasize that with this discussion we neither claim to provide an exhaustive argumentation nor blame any specific institution or individual on the raised issues. This is simply a discussion put forth by us, insiders of the machine learning field, reflecting on us.

show abstract

Section: Privacy-aware Aimentioning

confidence: 99%

HARK Side of Deep Learning -- From Grad Student Descent to Automated Machine Learning

Gencoglu¹,

Gils²,

Guldogan³

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…However, it is slower per operation and therefore, the results they presented are significantly less accurate (see Table 2). Boemer et al (2018) proposed an HE based extension to the Intel nGraph compiler. They use similar techniques to CryptoNets (Dowlin et al, 2016) with a different underlying encryption scheme, HEAAN (Cheon et al, 2017).…”

Section: Related Workmentioning

confidence: 99%

“…The accuracy is not reported inBoemer et al (2018). However, they implement the same network as inDowlin et al (2016).…”

mentioning

confidence: 99%

Low Latency Privacy Preserving Inference

Brutzkus

Elisha

Gilad-Bachrach

2018

Preprint

View full text Add to dashboard Cite

When applying machine learning to sensitive data, one has to find a balance between accuracy, information security, and computational-complexity. Recent studies combined Homomorphic Encryption with neural networks to make inferences while protecting against information leakage. However, these methods are limited by the width and depth of neural networks that can be used (and hence the accuracy) and exhibit high latency even for relatively simple networks. In this study we provide two solutions that address these limitations. In the first solution, we present more than 10× improvement in latency and enable inference on wider networks compared to prior attempts with the same level of security. The improved performance is achieved by novel methods to represent the data during the computation. In the second solution, we apply the method of transfer learning to provide private inference services using deep networks with latency of ∼ 0.16 seconds. We demonstrate the efficacy of our methods on several computer vision tasks.

show abstract

nGraph-HE: A Graph Compiler for Deep Learning on Homomorphically Encrypted Data

Cited by 2 publications

References 0 publications

HARK Side of Deep Learning -- From Grad Student Descent to Automated Machine Learning

HARK Side of Deep Learning -- From Grad Student Descent to Automated Machine Learning

Low Latency Privacy Preserving Inference

Contact Info

Product

Resources

About