Related papers: Generalization Techniques Empirically Outperform D…
Differential privacy (DP) is a popular mechanism for training machine learning models with bounded leakage about the presence of specific points in the training data. The cost of differential privacy is a reduction in the model's accuracy.…
To promote secure and private artificial intelligence (SPAI), we review studies on the model security and data privacy of DNNs. Model security allows system to behave as intended without being affected by malicious external influences that…
While being deployed in many critical applications as core components, machine learning (ML) models are vulnerable to various security and privacy attacks. One major privacy attack in this domain is membership inference, where an adversary…
Differential privacy is known to protect against threats to validity incurred due to adaptive, or exploratory, data analysis -- even when the analyst adversarially searches for a statistical estimate that diverges from the true value of the…
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…
Federated learning is a decentralized machine learning approach where clients train models locally and share model updates to develop a global model. This enables low-resource devices to collaboratively build a high-quality model without…
Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving…
Mechanisms used in privacy-preserving machine learning often aim to guarantee differential privacy (DP) during model training. Practical DP-ensuring training methods use randomization when fitting model parameters to privacy-sensitive data…
In distributed learning settings, models are iteratively updated with shared gradients computed from potentially sensitive user data. While previous work has studied various privacy risks of sharing gradients, our paper aims to provide a…
Differential privacy allows bounding the influence that training data records have on a machine learning model. To use differential privacy in machine learning, data scientists must choose privacy parameters $(\epsilon,\delta)$. Choosing…
Recent research shows that large language models are susceptible to privacy attacks that infer aspects of the training data. However, it is unclear if simpler generative models, like topic models, share similar vulnerabilities. In this…
Differential privacy (DP) has become the standard for private data analysis. Certain machine learning applications only require privacy protection for specific protected attributes. Using naive variants of differential privacy in such use…
Many machine learning applications are based on data collected from people, such as their tastes and behaviour as well as biological traits and genetic data. Regardless of how important the application might be, one has to make sure…
Data poisoning attacks aim to manipulate the model produced by a learning algorithm by adversarially modifying the training set. We consider differential privacy as a defensive measure against this type of attack. We show that such learners…
Membership inference attacks seek to infer membership of individual training instances of a model to which an adversary has black-box access through a machine learning-as-a-service API. In providing an in-depth characterization of…
Given a trained model and a data sample, membership-inference (MI) attacks predict whether the sample was in the model's training set. A common countermeasure against MI attacks is to utilize differential privacy (DP) during model training…
In this paper, an adjustment to the original differentially private stochastic gradient descent (DPSGD) algorithm for deep learning models is proposed. As a matter of motivation, to date, almost no state-of-the-art machine learning…
Deep learning models are often trained on datasets that contain sensitive information such as individuals' shopping transactions, personal contacts, and medical records. An increasingly important line of work therefore has sought to train…
Deep learning models have been extensively adopted in various regions due to their ability to represent hierarchical features, which highly rely on the training set and procedures. Thus, protecting the training process and deep learning…
Deep learning techniques based on neural networks have shown significant success in a wide range of AI tasks. Large-scale training datasets are one of the critical factors for their success. However, when the training datasets are…