Privacy & Security in ML

Record Linkage Using Metagenomic Microbiome Profiles

By Li I Wu
Posted on November 3, 2025

Problem Statement In healthcare, record linkage enables researchers to measure cross-sector care, assess care integration, and consider long-term outcomes from different sources. Deterministic linkage is applied when one or several identifiers can be used alone or in combination. However, these identifiers are not always reliable, as linkage errors can arise... [Read More]

Tags:

Securing DNN models deployed on edge devices with obfuscation

By Reema George Dass
Posted on April 2, 2024

Introduction The Obfuscation is a form of security via obscurity. In this context, obfuscation of DNN models deployed on edge devices such as mobile phones, computers, cameras, automotive gadgets, and any user-owned devices. If the user who owns the device on which the DNN model and code are copied locally,... [Read More]

Tags:

Machine Learning Fingerprinting

Enhancing Deep Neural Network Security

By Alexandra Posa
Posted on October 1, 2023

Fingerprinting is the process of embedding unique markers within a model to verify its authenticity and integrity. It not only facilitates the distinction between different users of the same model, enabling traceability and accountability, it also plays a crucial role in ensuring the secure deployment of machine learning models through... [Read More]

Tags:

Estimating the result count of queries using data synthesizers

By Aileen Dick
Posted on August 10, 2023

Data synthesizers Data synthetization is a widely used method to preserve privacy of personal data of individuals. Several models have been introduced to efficiently represent the underlying distributions and the inter-dependencies in data, which can be further used for generating artificial data to ensure the protection of personal data. Especially... [Read More]

Tags:

Increasing privacy for synthetic micro-data with Bayesian Networks

By Nina Niederhametner
Posted on February 6, 2023

Introduction The use of synthetic data as a privacy-preserving measure for micro-data is gaining more and more popularity, especially due to its ability to maintain data utility. Synthetic data is artificially generated by a model that has been trained on real data. This means that the observations in the synthetic... [Read More]

Tags: