Related papers: Learnability and Privacy Vulnerability are Entangl…

Deep Neural Nets (DNNs) have become a pervasive tool for solving many emerging problems. However, they tend to overfit to and memorize the training set. Memorization is of keen interest since it is closely related to several concepts such…

Machine learning models that are overfitted/overtrained are more vulnerable to knowledge leakage, which poses a risk to privacy. Suppose we download or receive a model from a third-party collaborator without knowing its training accuracy.…

Approximate machine unlearning aims to efficiently remove the influence of specific data points from a trained model, offering a practical alternative to full retraining. However, it introduces privacy risks: an adversary with access to…

Differential privacy (DP) is a gold-standard concept of measuring and guaranteeing privacy in data analysis. It is well-known that the cost of adding DP to deep learning model is its accuracy. However, it remains unclear how it affects…

Differentially private training algorithms provide protection against one of the most popular attacks in machine learning: the membership inference attack. However, these privacy algorithms incur a loss of the model's classification…

Sparse neural networks are mainly motivated by ressource efficiency since they use fewer parameters than their dense counterparts but still reach comparable accuracies. This article empirically investigates whether sparsity could also…

The huge computation demand of deep learning models and limited computation resources on the edge devices calls for the cooperation between edge device and cloud service by splitting the deep models into two halves. However, transferring…

The remarkable success of machine learning, especially deep learning, has produced a variety of cloud-based services for mobile users. Such services require an end user to send data to the service provider, which presents a serious…

Machine learning models leak information about the datasets on which they are trained. An adversary can build an algorithm to trace the individual members of a model's training dataset. As a fundamental inference attack, he aims to…

The memorization of training data by neural networks raises pressing concerns for privacy and security. Recent work has shown that, under certain conditions, portions of the training set can be reconstructed directly from model parameters.…

Membership inference attacks seek to infer the membership of individual training instances of a privately trained model. This paper presents a membership privacy analysis and evaluation system, called MPLens, with three unique…

We show that the influence of a subset of the training samples can be removed -- or "forgotten" -- from the weights of a network trained on large-scale image classification tasks, and we provide strong computable bounds on the amount of…

With the recent surge of social networks like Facebook, new forms of recommendations have become possible -- personalized recommendations of ads, content, and even new social and product connections based on one's social interactions. In…

Attacks that aim to identify the training data of public neural networks represent a severe threat to the privacy of individuals participating in the training data set. A possible protection is offered by anonymization of the training data…

A deep learning model usually has to sacrifice some utilities when it acquires some other abilities or characteristics. Privacy preservation has such trade-off relationships with utilities. The loss disparity between various defense…

Membership inference attacks (MIAs) are used to test practical privacy of machine learning models. MIAs complement formal guarantees from differential privacy (DP) under a more realistic adversary model. We analyse MIA vulnerability of…

In collaborative learning, clients keep their data private and communicate only the computed gradients of the deep neural network being trained on their local data. Several recent attacks show that one can still extract private information…

Membership inference attacks (MIAs) pose a critical threat to the privacy of training data in deep learning. Despite significant progress in attack methodologies, our understanding of when and how models encode membership information during…

Privacy-preserving training on sensitive data commonly relies on differentially private stochastic optimization with gradient clipping and Gaussian noise. The clipping threshold is a critical control knob: if set too small, systematic…

Hierarchical text classification consists in classifying text documents into a hierarchy of classes and sub-classes. Although artificial neural networks have proved useful to perform this task, unfortunately they can leak training data…