COSIC Seminar: Privacy-Preserving Neural Network Classification by Orhan Ermis

COSIC Seminar – Privacy-preserving Neural Network Classification – Orhan Ermis (Eurecom) With the advent of the big data technologies which bring better scalability and performance results, machine learning (ML) algorithms become affordable in a number of different applications and areas. The use of large volumes of data to obtain accurate predictions unfortunately come with a high cost in terms of privacy exposures. The underlying data are often personal or confidential and therefore need to be properly safeguarded. Given the cost of machine learning algorithms, these would need to be outsourced to third-party servers and hence the encryption of the data becomes mandatory. While traditional data encryption solutions would not allow for the access over the content of the data, these would, nevertheless, prevent third-party servers to properly execute the ML algorithms. The goal is therefore to come up with customized ML algorithms (i.e. neural network classification) that would by design preserve the privacy of the processed data. Advanced cryptographic techniques such as fully homomorphic encryption or secure multi-party computation enable the execution of some operations over encrypted data and therefore can be considered as potential candidates for these algorithms. Yet, these incur high computational and/or communication costs for some operations. In this presentation, first, the privacy preserving arrhythmia classification based on secure multy-party computation will be introduced. Later, benchmarks on well-known advanced cryptographic techniques for particular neural network classification tasks will be given. Finally, an extended setting to show the applicability of privacy preserving neural network classification in real-life application scenarios will be introduced. Short-bio: Orhan Ermiss is a postdoctoral researcher in the Digital Security Department at EURECOM. Previously, he was a postdoctoral researcher at Boğaziçi University, where he received his PhD degree in 2017. Dr. Ermis received his BS and MS degrees from Bahçeşehir University, Computer Engineering Department in 2005 and 2007, respectively. His research interest includes cryptographic protocols, applied cryptography, privacy-preserving machine learning, network security and machine learning implementations for security.