Efficient Methods for Privacy Preserving Face Detection

Abstract

Bob offers a face-detection web service where clients can submit their images for analysis. Alice would very much like to use the service, but is reluctant to reveal the content of her images to Bob. Bob, for his part, is reluctant to release his face detector, as he spent a lot of time, energy and money constructing it. Secure Multi-Party computations use cryptographic tools to solve this problem without leaking any information. Unfortunately, these methods are slow to compute and we introduce a couple of machine learning techniques that allow the parties to solve the problem while leaking a controlled amount of information. The first method is an information-bottleneck variant of AdaBoost that lets Bob find a subset of features that are enough for classifying an image patch, but not enough to actually reconstruct it. The second machine learning technique is active learning that allows Alice to construct an online classifier, based on a small number of calls to Bob's face detector. She can then use her online classifier as a fast rejector before using a cryptographically secure classifier on the remaining image patches.

Assessment of differentially private synthetic data for utility and fairness in end-to-end machine learning pipelines for tabular data

“…We examine fairness performance through three different perspectives. Previous research [ 20 ] has indicated that differentially private machine learning models tend to perform worse on minority groups. To this point we evaluate the decay in accuracy for the different subgroups in the protected attribute.…”

“…By performance, we mean not only the utility of the model (its accuracy, for example) but also how well the model performs for different subgroups of the dataset-the fairness of the model. The impact of machine learning models on minorities subgroups is an active area of research, and several works have investigated the trade-offs among model accuracy, bias, and privacy [19][20][21][22]. However, only recently bias caused by the use of synthetic data in downstream classification received attention [9,23,24].…”

Improving Privacy and Utility in Aggregate Data: A Hybrid Approach

“…The performance of the PoolDiv mechanism is on par with traditional DP approaches for low-dimensional data regression and excels in high-dimensional data synthesis. [21, 22, 23]…”

Predictive modelling of brain disorders with magnetic resonance imaging: A systematic review of modelling practices, transparency, and interpretability in the use of convolutional neural networks

“…Deep learning models optimize an objective function over a set of arguments, meaning that any decisions taken in preprocessing and model construction can affect the capabilities of the system as a whole, and propagate subjective choices throughout ostensibly objective models (Hooker, 2021). For instance, several studies have examined algorithmic biases against underrepresented and/or marginalised groups (Bagdasaryan et al, 2019; Buolamwini & Gebru, 2018; Diakopoulos, 2015). Aside from domain‐specific benefits to code sharing, the larger scientific community has recently shifted towards open science frameworks, with several high‐profile journals requiring methodological transparency (Eglen et al, 2017; Stodden, 2011; Nature editorial policies, 2021; Science editorial policies, 2021).…”