Secured Computation – Analyzing Sensitive Data using Homomorphic Encryption
Who is this presentation for?Data Scientist, Security Engineers
Organizations often work with sensitive information such as social security number, and Credit card information. Although this data is stored in encrypted form, most analytical operations ranging from data analysis to advanced machine learning algorithms require data decryption for computation. This creates unwanted exposures to theft or unauthorized read by undesirables. In this session, we present a use case that prevents fraudulent victimization of our customers, implemented in real-time, using secured computations enabled through homomorphic encryption.
Cox Communications is a privately-owned subsidiary of Cox Enterprises providing digital cable television, telecommunications and Home Automation services in the United States. It is the third-largest cable television provider in the United States serving more than 6.2 million customers.
Fraud victimization is one form of economic crime largely executed by deception. The most common being identification impersonation and/or using unauthorized credit cards. In this case study we will explore in detail how homomorphic encryption is helping to tackle these issues by avoiding decryption of personal data while minimizing risk of exposure.
Homomorphic encryption gives organizations a secure and easy way to run analytics on data without having to decrypt it. It does this by providing computation capability on the encrypted ciphertext, generating an encrypted result which, when decrypted, matches the result of the operations as if they had been performed on the plaintext.
In this presentation we will focus on two use cases. The first case identifies exact identification match and generating alerts if there is mis-match based on pre-defined attributes. The second use case covers typographical inputs or communication misinterpretation scenarios by identifying proximal identification matches using a combination of Levenshtein distance and Jaro–Winkler distance. Additionally, we will share the following topics;
1. High-level solution architecture for secure computation
2. Using Containers and GPU’s to provide real-time information
3. Challenges in working with homomorphic encrypted data and performance
Cox Communications Contributors:
Matt Carothers, Jignesh Patel, and Harry Tang
Prerequisite knowledgeData Encryption
What you'll learn
Matt is a Security Principal at Cox Communications. He holds Patents on: Weighted Data Packet Communication System, Systems and Methods of DNS Grey Listing, and Systems and Methods of Mapped Network Address Translation
Jignesh is a Principal Architect at Cox Communications and this is his first time at SCTE. He has more than 15 years’ experience in applying scientific methods and mathematical models to solve problems concerning the management of systems, people, machines, materials and finance in industry. Previously he has been a trusted advisor for large software company in the North-West assisting in data center capacity forecasting and providing machine learning capabilities to detect email spam, predicting DDOS attack and preventing DNS blackhole.
Leave a Comment or Question
Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?
Join the conversation here (requires login)
For conference registration information and customer service
For more information on community discounts and trade opportunities with O’Reilly conferences
For information on exhibiting or sponsoring a conference
View a complete list of Strata Data Conference contacts