相关论文: PASS: Private Attributes Protection with Stochasti…

Speech data is expensive to collect, and incredibly sensitive to its sources. It is often the case that organizations independently collect small datasets for their own use, but often these are not performant for the demands of machine…

Despite the growing interest in unsupervised learning, extracting meaningful knowledge from unlabelled audio remains an open challenge. To take a step in this direction, we recently proposed a problem-agnostic speech encoder (PASE), that…

Differential privacy (DP) is typically formulated as a worst-case privacy guarantee over all individuals in a database. More recently, extensions to individual subjects or their attributes, have been introduced. Under the…

Machine Learning-as-a-Service (MLaaS) has become a widespread paradigm, making even the most complex machine learning models available for clients via e.g. a pay-per-query principle. This allows users to avoid time-consuming processes of…

Ensuring the privacy of training data is a growing concern since many machine learning models are trained on confidential and potentially sensitive data. Much attention has been devoted to methods for protecting individual privacy during…

Objective: To enable privacy-preserving learning of high quality generative and discriminative machine learning models from distributed electronic health records. Methods and Results: We describe general and scalable strategy to build…

As machine learning has become more relevant for everyday applications, a natural requirement is the protection of the privacy of the training data. When the relevant learning questions are unknown in advance, or hyper-parameter tuning…

Applying a randomized algorithm to a subset rather than the entire dataset amplifies privacy guarantees. We propose a class of subsampling methods ``MUltistage Sampling Technique (MUST)'' for privacy amplification (PA) in the context of…

The explosive growth of machine learning has made it a critical infrastructure in the era of artificial intelligence. The extensive use of data poses a significant threat to individual privacy. Various countries have implemented…

While deep learning models have shown significant performance across various domains, their deployment needs extensive resources and advanced computing infrastructure. As a solution, Machine Learning as a Service (MLaaS) has emerged,…

Machine learning (ML) methods are widely used in industrial applications, which usually require a large amount of training data. However, data collection needs extensive time costs and investments in the manufacturing system, and data…

Split Learning (SL) is a collaborative learning approach that improves privacy by keeping data on the client-side while sharing only the intermediate output with a server. However, the distributed nature of SL introduces new security…

In recent years, machine learning neural network has penetrated deeply into people's life. As the price of convenience, people's private information also has the risk of disclosure. The "right to be forgotten" was introduced in a timely…

The availability of large amounts of user-provided data has been key to the success of machine learning for many real-world tasks. Recently, an increasing awareness has emerged that users should be given more control about how their data is…

In recent years, formal methods of privacy protection such as differential privacy (DP), capable of deployment to data-driven tasks such as machine learning (ML), have emerged. Reconciling large-scale ML with the closed-form reasoning…

Machine learning models are vulnerable to simple model stealing attacks if the adversary can obtain output labels for chosen inputs. To protect against these attacks, it has been proposed to limit the information provided to the adversary…

Split learning (SL) is a new collaborative learning technique that allows participants, e.g. a client and a server, to train machine learning models without the client sharing raw data. In this setting, the client initially applies its part…

Machine unlearning has become a promising solution for fulfilling the "right to be forgotten", under which individuals can request the deletion of their data from machine learning models. However, existing studies of machine unlearning…

Machine learning (ML) applications are increasingly prevalent. Protecting the confidentiality of ML models becomes paramount for two reasons: (a) a model can be a business advantage to its owner, and (b) an adversary may use a stolen model…

We investigate an attack on a machine learning model that predicts whether a person or household will relocate in the next two years, i.e., a propensity-to-move classifier. The attack assumes that the attacker can query the model to obtain…