Sensitive Data Masking in Images

In today’s digital era, images play a prominent role in information sharing. Currently, we are exchanging a huge amount of data with sensitive information as images. It can be in the form of a digital identity proof submission for online applications like creating a bank account or as the number plate images captured at a traffic signal. Government authorities and various business organizations store and assess these data.

Broadly, these images are sources of Personally Identifiable Information (PII). Organizations need to protect sensitive data in compliance with regulatory compliances such as GDPR and PCI DSS. Image masking is one such technique to implement these regulations.

Identifying Sensitive Data in Images

Although there are many ways to mask sensitive data present in images, we will discuss how we obfuscate sensitive data with random data. It is a two-step process: the first step is to identify the sensitive data using the ‘Data Discovery’ feature of iEDPS. The sensitive data layout in images is recognized using the Optical Character Recognition (OCR) technique as a part of Computer Vision. Then, the identified section is processed and transformed into machine-readable text using deep learning techniques such as LSTM and Recurrent Neural Networks (RNN). We can either choose to create a copy of the image with the highlighted sensitive data or directly create their masked copies.

Masking Sensitive Data in Images

After identifying the sensitive data, the next step is to apply different masking techniques using the iEDPS masking engine to obfuscate the selected sections. iEDPS also supports deterministic techniques to ensure the masked data on the images are consistent with the masked data in databases or other flat files.

iEDPS supports discovery and masking on a variety of images such as receipts, bank cheques, etc.

Below is an example of ‘Image Masking’ with the amount field being masked:

In conclusion, as images are increasingly being used in various fields such as banking and financial services, surveillance, academia, and others, regulatory compliance to protect data becomes a necessity. With the ‘Data Discovery’ and ‘Masking’ features, iEDPS provide a single-stop solution for identifying and protecting sensitive data in images.

 

Infosys PrivacyNext aims to build a Privacy First Organization leveraging global talent, strategic partnerships, and best-in-class privacy-enhancing technologies to minimize data risk. The platform is powered by Infosys Enterprise Data Privacy Suite (iEDPS).

iEDPS provides enterprise-class data privacy capabilities and enables an organization to adhere to global regulatory standards such as GDPR, CCPA, HIPAA, PIPEDA, GLBA, ITAR, other global and local regulations.

Loaded with deterministic, selective, dynamic, and static masking features, Data Discovery, and Data Generation capabilities, iEDPS can be deployed on any platform and supports all major databases and file systems.

For more details check out the below links:

LinkedIn: https://www.linkedin.com/company/infosys-enterprise-data-privacy-suite-iedps/

Infosys Official Page: https://www.infosys.com/services/incubating-emerging-technologies/offerings/enterprise-data-privacy-suite.html

Author Details

Purva Porwal

Purva Porwal is Technology Lead at Infosys Center for Emerging Technology Solutions. She works on iEDPS product development in AI/ML domain.

Leave a Comment

Your email address will not be published.