Related papers: Measuring Data Leakage in Machine-Learning Models …
Across many disciplines, causal inference often relies on randomized experiments with binary outcomes. In such experiments, the Fisher randomization test provides exact, assumption-free tests for causal effects. Sometimes the outcomes are…
Machine learning models are vulnerable to both security attacks (e.g., adversarial examples) and privacy attacks (e.g., private attribute inference). We take the first step to mitigate both the security and privacy attacks, and maintain…
As machine learning becomes a practice and commodity, numerous cloud-based services and frameworks are provided to help customers develop and deploy machine learning applications. While it is prevalent to outsource model training and…
In the evolving landscape of machine learning (ML), Federated Learning (FL) presents a paradigm shift towards decentralized model training while preserving user data privacy. This paper introduces the concept of ``privacy drift", an…
Image recognition systems have demonstrated tremendous progress over the past few decades thanks, in part, to our ability of learning compact and robust representations of images. As we witness the wide spread adoption of these systems, it…
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 steadily growing over the past few years, research on the privacy…
The increasing availability of online and mobile information platforms is facilitating the development of peer-to-peer collaboration strategies in large-scale networks. These technologies are being leveraged by networked robotic systems to…
Twenty-eight within-subject counterfactual experiments across 2,047 tabular datasets, plus a boundary experiment on 129 temporal datasets, measuring the severity of four data leakage classes in machine learning. Class I (estimation -…
The problem of preserving the privacy of individual entries of a database when responding to linear or nonlinear queries with constrained additive noise is considered. For privacy protection, the response to the query is systematically…
We introduce a privacy measure called statistic maximal leakage that quantifies how much a privacy mechanism leaks about a specific secret, relative to the adversary's prior information about that secret. Statistic maximal leakage is an…
This paper provides a systematic approach to semiparametric identification that is based on statistical information as a measure of its "quality". Identification can be regular or irregular, depending on whether the Fisher information for…
The growing use of machine learning (ML) has raised concerns that an ML model may reveal private information about an individual who has contributed to the training dataset. To prevent leakage of sensitive data, we consider using…
Transfer learning has become an increasingly popular technique in machine learning as a way to leverage a pretrained model trained for one task to assist with building a finetuned model for a related task. This paradigm has been especially…
Transfer learning is a useful machine learning framework that allows one to build task-specific models (student models) without significantly incurring training costs using a single powerful model (teacher model) pre-trained with a large…
Recommender models are hard to evaluate, particularly under offline setting. In this paper, we provide a comprehensive and critical analysis of the data leakage issue in recommender system offline evaluation. Data leakage is caused by not…
Frontier AI systems are making transformative impacts across society, but such benefits are not without costs: models trained on web-scale datasets containing personal and private data raise profound concerns about data privacy and…
Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…
Machine Learning models, extensively used for various multimedia applications, are offered to users as a blackbox service on the Cloud on a pay-per-query basis. Such blackbox models are commercially valuable to adversaries, making them…
Modern machine learning systems use models trained on ever-growing corpora. Typically, metadata such as ownership, access control, or licensing information is ignored during training. Instead, to mitigate privacy risks, we rely on generic…
Distributed machine learning paradigms, such as federated learning, have been recently adopted in many privacy-critical applications for speech analysis. However, such frameworks are vulnerable to privacy leakage attacks from shared…