Related papers: Rethinking Privacy in Machine Learning Pipelines f…
Organizations are collecting vast amounts of data, but they often lack the capabilities needed to fully extract insights. As a result, they increasingly share data with external experts, such as analysts or researchers, to gain value from…
With the growing adoption of privacy-preserving machine learning algorithms, such as Differentially Private Stochastic Gradient Descent (DP-SGD), training or fine-tuning models on private datasets has become increasingly prevalent. This…
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…
Privacy-preserving machine learning (ML) seeks to balance data utility and privacy, especially as regulations like the GDPR mandate the anonymization of personal data for ML applications. Conventional anonymization approaches often reduce…
Machine Learning (ML) is crucial in many sectors, including computer vision. However, ML models trained on sensitive data face security challenges, as they can be attacked and leak information. Privacy-Preserving Machine Learning (PPML)…
The rapid advancements in artificial intelligence (AI) have primarily focused on the process of learning from data to acquire knowledgeable learning systems. As these systems are increasingly deployed in critical areas, ensuring their…
In supervised machine learning, privileged information (PI) is information that is unavailable at inference, but is accessible during training time. Research on learning using privileged information (LUPI) aims to transfer the knowledge…
In this thesis we consider the problem of information hiding in the scenarios of interactive systems, statistical disclosure control, and refinement of specifications. We apply quantitative approaches to information flow in the first two…
Machine unlearning, the process of selectively removing data from trained models, is increasingly crucial for addressing privacy concerns and knowledge gaps post-deployment. Despite this importance, existing approaches are often heuristic…
Machine learning poses severe privacy concerns as it has been shown that the learned models can reveal sensitive information about their training data. Many works have investigated the effect of widely adopted data augmentation and…
The classical machine learning paradigm requires the aggregation of user data in a central location where machine learning practitioners can preprocess data, calculate features, tune models and evaluate performance. The advantage of this…
The recent success of machine learning (ML) has been fueled by the increasing availability of computing power and large amounts of data in many different applications. However, the trustworthiness of the resulting models can be compromised…
Data-driven control offers a viable option for control scenarios where constructing a system model is expensive or time-consuming. Nonetheless, many of these algorithms are not entirely automated, often necessitating the adjustment of…
Several domains increasingly rely on machine learning in their applications. The resulting heavy dependence on data has led to the emergence of various laws and regulations around data ethics and privacy and growing awareness of the need…
In the classical multi-party computation setting, multiple parties jointly compute a function without revealing their own input data. We consider a variant of this problem, where the input data can be shared for machine learning training…
Models need to be trained with privacy-preserving learning algorithms to prevent leakage of possibly sensitive information contained in their training data. However, canonical algorithms like differentially private stochastic gradient…
Automated machine learning techniques benefited from tremendous research progress in recently. These developments and the continuous-growing demand for machine learning experts led to the development of numerous AutoML tools. However, these…
As datasets become critical assets in modern machine learning systems, ensuring robust copyright protection has emerged as an urgent challenge. Traditional legal mechanisms often fail to address the technical complexities of digital data…
Large Language Models are typically trained on datasets collected from the web, which may inadvertently contain harmful or sensitive personal information. To address growing privacy concerns, unlearning methods have been proposed to remove…
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…