Related papers: Algorithms that Remember: Model Inversion Attacks …

Data and derived information about target victims has always been key for successful attacks, both during historical wars and modern cyber wars. Ours turns out to be an era in which modern cars generate a plethora of data about their…

Artificial Intelligence (AI) is making a profound impact in almost every domain. One of the crucial factors contributing to this success has been the access to an abundance of high-quality data for constructing machine learning models.…

Recent advances in machine learning, particularly in Natural Language Processing (NLP), have produced powerful models trained on vast datasets. However, these models risk leaking sensitive information, raising privacy concerns. In response,…

Powerful recognition algorithms are widely used in the Internet or important medical systems, which poses a serious threat to personal privacy. Although the law provides for diversity protection, e.g. The General Data Protection Regulation…

Machine learning as a service (MLaaS), and algorithm marketplaces are on a rise. Data holders can easily train complex models on their data using third party provided learning codes. Training accurate ML models requires massive labeled data…

Transformative AI systems may pose unprecedented catastrophic risks, but the U.S. Constitution places significant constraints on the government's ability to govern this technology. This paper examines how the First Amendment, administrative…

The rapid progress of AI, combined with its unprecedented public adoption and the propensity of large neural networks to memorize training data, has given rise to significant data privacy concerns. To address these concerns, machine…

Artificial Intelligence (AI) is increasingly used to make important decisions about people. While issues of AI bias and proxy discrimination are well explored, less focus has been paid to the harms created by profiling based on groups that…

Machine learning algorithms are used to construct a mathematical model for a system based on training data. Such a model is capable of making highly accurate predictions without being explicitly programmed to do so. These techniques have a…

Machine learning algorithms, when applied to sensitive data, pose a potential threat to privacy. A growing body of prior work has demonstrated that membership inference attack (MIA) can disclose specific private information in the training…

Model Inversion (MI), in which an adversary abuses access to a trained Machine Learning (ML) model attempting to infer sensitive information about its original training data, has attracted increasing research attention. During MI, the…

Machine learning models' goal is to make correct predictions for specific tasks by learning important properties and patterns from data. By doing so, there is a chance that the model learns properties that are unrelated to its primary task.…

Machine learning (ML) is becoming a commodity. Numerous ML frameworks and services are available to data holders who are not ML experts but want to train predictive models on their data. It is important that ML models trained on sensitive…

This PhD thesis discusses how European law could improve privacy protection in the area of behavioural targeting. Behavioural targeting, also referred to as online profiling, involves monitoring people's online behaviour, and using the…

The General Data Protection Regulation (GDPR) forces IT companies to comply with a number of principles when dealing with European citizens' personal data. Non-compliant companies are exposed to penalties which may represent up to 4% of…

Growing recognition of the potential for exploitation of personal data and of the shortcomings of prior privacy regimes has led to the passage of a multitude of new online privacy regulations. Some of these laws -- notably the European…

Data privacy is an important issue for "machine learning as a service" providers. We focus on the problem of membership inference attacks: given a data sample and black-box access to a model's API, determine whether the sample existed in…

Generative models learn the distribution of data from a sample dataset and can then generate new data instances. Recent advances in deep learning has brought forth improvements in generative model architectures, and some state-of-the-art…

Decisions such as which movie to watch next, which song to listen to, or which product to buy online, are increasingly influenced by recommender systems and user models that incorporate information on users' past behaviours, preferences,…

The raise of machine learning and deep learning led to significant improvement in several domains. This change is supported by both the dramatic rise in computation power and the collection of large datasets. Such massive datasets often…