As machine learning becomes more widely used, the need to study its implications in
security and privacy becomes more urgent. Although the body of work in privacy has been …

Machine-Learning-as-a-Service (MLaaS) has become a widespread paradigm, making
even the most complex Machine Learning models available for clients via, eg, a pay-per …

Most current approaches for protecting privacy in machine learning (ML) assume that
models exist in a vacuum. Yet, in reality, these models are part of larger systems that include …

Training machine learning (ML) models is expensive in terms of computational power,
amounts of labeled data and human expertise. Thus, ML models constitute business value …

Abstract Model distillation is frequently proposed as a technique to reduce the privacy
leakage of machine learning. These empirical privacy defenses rely on the intuition that …

Abstract Data-Free Model Extraction (DFME) aims to clone a black-box model without
knowing its original training data distribution, making it much easier for attackers to steal …

The concerns on visual privacy have been increasingly raised along with the dramatic
growth in image and video capture and sharing. Meanwhile, with the recent breakthrough in …

Abstract Model stealing attacks present a dilemma for public machine learning APIs. To
protect financial investments, companies may be forced to withhold important information …

Abstract Model stealing (MS) involves querying and observing the output of a machine
learning model to steal its capabilities. The quality of queried data is crucial yet obtaining a …

Cloud service providers, including Google, Amazon, and Alibaba, have now launched
machinelearning-as-a-service (MLaaS) platforms, allowing clients to access sophisticated …