Privacy-Preserving ECG Classification With Branching Programs and Neural Networks

Barni, Mauro; Failla, Pierluigi; Lazzeretti, Riccardo; Sadeghi, Ahmad-Reza; Schneider, Thomas

doi:10.1109/tifs.2011.2108650

Cited by 160 publications

(76 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The training algorithm is the same as in the non-privacy-preserving case, thus the resulting models are as vulnerable to inference attacks as any conventionally trained model. This also holds for the models trained by computing on encrypted data [4], [6], [35].…”

Section: Related Workmentioning

confidence: 96%

“…Examples include Google Prediction API, 1 Amazon Machine Learning (Amazon ML), 2 Microsoft Azure Machine Learning (Azure ML), 3 and BigML. 4 These platforms provide simple APIs for uploading the data and for training and querying models, thus making machine learning technologies available to any customer. For example, a developer may create an app that gathers data from users, uploads it into the cloud platform to train a model (or update an existing model with new data), and then uses the model's predictions inside the app to improve its features or better interact with the users.…”

Section: Machine Learning Backgroundmentioning

confidence: 99%

See 1 more Smart Citation

Membership Inference Attacks Against Machine Learning Models

Shokri

Stronati

Song

et al. 2017

2017 IEEE Symposium on Security and Privacy (SP)

2,766

2,817

View full text Add to dashboard Cite

Abstract-We quantitatively investigate how machine learning models leak information about the individual data records on which they were trained. We focus on the basic membership inference attack: given a data record and black-box access to a model, determine if the record was in the model's training dataset. To perform membership inference against a target model, we make adversarial use of machine learning and train our own inference model to recognize differences in the target model's predictions on the inputs that it trained on versus the inputs that it did not train on.We empirically evaluate our inference techniques on classification models trained by commercial "machine learning as a service" providers such as Google and Amazon. Using realistic datasets and classification tasks, including a hospital discharge dataset whose membership is sensitive from the privacy perspective, we show that these models can be vulnerable to membership inference attacks. We then investigate the factors that influence this leakage and evaluate mitigation strategies.

show abstract

Section: Related Workmentioning

confidence: 96%

Section: Machine Learning Backgroundmentioning

confidence: 99%

Membership Inference Attacks Against Machine Learning Models

Shokri

Stronati

Song

et al. 2017

2017 IEEE Symposium on Security and Privacy (SP)

2,766

2,817

View full text Add to dashboard Cite

show abstract

“…Step 2: Divide all the prediction errors into L clusters C k , for 0 ≤ k ≤ L − 1, where k is determined by (5), and each C k is formed by concatenating the mapped prediction errors in a raster-scan order.…”

Section: A Image Encryption Via Prediction Error Clustering and Randmentioning

confidence: 99%

“…. s16, where the numbers within the blocks denote the indexes of the elements of S. Before permutation, the first row becomes (1, 2, 3, 4), the second row becomes (5,6,7,8), etc. The column shifts are specified by a key vector CS = [2 3 0 1], with each column undergoing a downward cyclical shift in accordance with the key value associated with that column.…”

Section: A Image Encryption Via Prediction Error Clustering and Randmentioning

confidence: 99%

Designing an Efficient Image Encryption-then Compression System

Suneetha¹

2015

International Journal of Innovative Research in Electrical, Ele

View full text Add to dashboard Cite

Abstract:In many practical scenarios, image encryption has to be conducted prior to image compression. This has led to the problem of how to design a pair of image encryption and compression algorithms such that compressing the encrypted images can still be efficiently performed. In this paper, we design a highly efficient image encryption-thencompression (ETC) system, where both lossless and lossy compressions are considered. The proposed image encryption scheme operated in the prediction error domain is shown to be able to provide a reasonably high level of security. We also demonstrate that an arithmetic coding-based approach can be exploited to efficiently compress the encrypted images. More notably, the proposed compression approach applied to encrypted images is only slightly worse, in terms of compression efficiency, than the state-of-the-art lossless/lossy image coders, which take original, unencrypted images as inputs. In contrast, most of the existing ETC solutions induce significant penalty on the compression efficiency.

show abstract

“…In [27] the focus is on the analysis of ECG data by a remote server. The security set-up considers a situation in which the server is asked to elaborate a diagnosis by relying on the ECG profile, without learning anything about the profile and even the output of diagnosis.…”

Section: Other Emerging Applicationsmentioning

confidence: 99%

Emerging cryptographic challenges in image and video processing

Puech

Erkin

Barni

et al. 2012

2012 19th IEEE International Conference on Image Processing

View full text Add to dashboard Cite

Puech, W.; Erkin, Z.; Barni, M.; Rane, S.; Lagendijk, R.L. TR2012-067 September 2012 AbstractIn an increasing number of image and video processing problems, cryptographic techniques are used to enforce content access control, identity verification and authentication, and privacy protection. The combination of cryptography and signal processing is an exciting emerging field. This introductory paper gives an overview of approaches and challenges that exist in applying cryptographic primitives to important image and video processing problems, including (partial) content encryption, secure face recognition, and secure biometrics. This paper aims to help the community in appreciating the utility and challenges of cryptographic techniques in image and video processing. IEEE International Conference on Image Processing (ICIP)This work may not be copied or reproduced in whole or in part for any commercial purpose. Permission to copy in whole or in part without payment of fee is granted for nonprofit educational and research purposes provided that all such whole or partial copies include the following: a notice that such copying is by permission of Mitsubishi Electric Research Laboratories, Inc.; an acknowledgment of the authors and individual contributions to the work; and all applicable portions of the copyright notice. Copying, reproduction, or republishing for any other purpose shall require a license with payment of fee to Mitsubishi Electric Research Laboratories, Inc. All rights reserved. ABSTRACTIn an increasing number of image and video processing problems, cryptographic techniques are used to enforce content access control, identity verification and authentication, and privacy protection. The combination of cryptography and signal processing is an exciting emerging field. This introductory paper gives an overview of approaches and challenges that exist in applying cryptographic primitives to important image and video processing problems, including (partial) content encryption, secure face recognition, and secure biometrics. This paper aims to help the community in appreciating the utility and challenges of cryptographic techniques in image and video processing.

show abstract

Privacy-Preserving ECG Classification With Branching Programs and Neural Networks

Cited by 160 publications

References 45 publications

Membership Inference Attacks Against Machine Learning Models

Membership Inference Attacks Against Machine Learning Models

Designing an Efficient Image Encryption-then Compression System

Emerging cryptographic challenges in image and video processing

Contact Info

Product

Resources

About