arXiv subjects

Rudolf Mayer

Publications and source records attributed to Rudolf Mayer.

9 recordsLinked to original sources

arXiv2026

S4CMDR: a metadata repository for electronic health records

Background: Electronic health records (EHRs) enable machine learning for diagnosis, prognosis, and clinical decision support. However, EHR standards vary by country and hospital, making records often incompatible. This limits large-scale and cross-clinical machine learning. To address such complexity, a metadata repository cataloguing available data elements, their value domains, and their compatibility is an essential tool. This allows researchers to leverage relevant data for tasks such as identifying undiagnosed rare disease patients. Results: Within the Screen4Care project, we developed S4CMDR, an open-source metadata repository built on ISO 11179-3, based on a middle-out metadata standardisation approach. It automates cataloguing to reduce errors and enable the discovery of compatible feature sets across data registries. S4CMDR supports on-premise Linux deployment and cloud hosting, with state-of-the-art user authentication and an accessible interface. Conclusions: S4CMDR is a clinical metadata repository registering and discovering compatible EHR records. Novel contributions include a microservice architecture, a middle-out standardisation approach, and a user-friendly interface for error-free data registration and visualisation of metadata compatibility. We validate S4CMDR's case studies involving rare disease patients. We invite clinical data holders to populate S4CMDR using their metadata to validate the generalisability and support further development.

cs.IR↗

arXiv2025

I Stolenly Swear That I Am Up to (No) Good: Design and Evaluation of Model Stealing Attacks

Model stealing attacks endanger the confidentiality of machine learning models offered as a service. Although these models are kept secret, a malicious party can query a model to label data samples and train their own substitute model, violating intellectual property. While novel attacks in the field are continually being published, their design and evaluations are not standardised, making it challenging to compare prior works and assess progress in the field. This paper is the first to address this gap by providing recommendations for designing and evaluating model stealing attacks. To this end, we study the largest group of attacks that rely on training a substitute model -- those attacking image classification models. We propose the first comprehensive threat model and develop a framework for attack comparison. Further, we analyse attack setups from related works to understand which tasks and models have been studied the most. Based on our findings, we present best practices for attack development before, during, and beyond experiments and derive an extensive list of open research questions regarding the evaluation of model stealing attacks. Our findings and recommendations also transfer to other problem domains, hence establishing the first generic evaluation methodology for model stealing attacks.

cs.CR↗

arXiv2025

NCorr-FP: A Neighbourhood-based Correlation-preserving Fingerprinting Scheme for Intellectual Property Protection of Structured Data

Ensuring data ownership and traceability of unauthorised redistribution are central to safeguarding intellectual property in shared data environments. Data fingerprinting addresses these challenges by embedding recipient-specific marks into the data, typically via content modifications. We propose NCorr-FP, a Neighbourhood-based Correlation-preserving Fingerprinting system for structured tabular data with the main goal of preserving statistical fidelity. The method uses local record similarity and density estimation to guide the insertion of fingerprint bits. The embedding logic is then reversed to extract the fingerprint from a potentially modified dataset. Extensive experiments confirm its effectiveness, fidelity, utility and robustness. Results show that fingerprints are virtually imperceptible, with minute Hellinger distances and KL divergences, even at high embedding ratios. The system also maintains high data utility for downstream predictive tasks. The method achieves 100\% detection confidence under substantial data deletions and remains robust against adaptive and collusion attacks. Satisfying all these requirements concurrently on mixed-type datasets highlights the strong applicability of NCorr-FP to real-world data settings.

cs.CR↗

arXiv2025

Attackers Can Do Better: Over- and Understated Factors of Model Stealing Attacks

Machine learning models were shown to be vulnerable to model stealing attacks, which lead to intellectual property infringement. Among other methods, substitute model training is an all-encompassing attack applicable to any machine learning model whose behaviour can be approximated from input-output queries. Whereas prior works mainly focused on improving the performance of substitute models by, e.g. developing a new substitute training method, there have been only limited ablation studies on the impact the attacker's strength has on the substitute model's performance. As a result, different authors came to diverse, sometimes contradicting, conclusions. In this work, we exhaustively examine the ambivalent influence of different factors resulting from varying the attacker's capabilities and knowledge on a substitute training attack. Our findings suggest that some of the factors that have been considered important in the past are, in fact, not that influential; instead, we discover new correlations between attack conditions and success rate. In particular, we demonstrate that better-performing target models enable higher-fidelity attacks and explain the intuition behind this phenomenon. Further, we propose to shift the focus from the complexity of target models toward the complexity of their learning tasks. Therefore, for the substitute model, rather than aiming for a higher architecture complexity, we suggest focusing on getting data of higher complexity and an appropriate architecture. Finally, we demonstrate that even in the most limited data-free scenario, there is no need to overcompensate weak knowledge with millions of queries. Our results often exceed or match the performance of previous attacks that assume a stronger attacker, suggesting that these stronger attacks are likely endangering a model owner's intellectual property to a significantly higher degree than shown until now.

cs.LG↗

arXiv2024

U Can't Gen This? A Survey of Intellectual Property Protection Methods for Data in Generative AI

Large Generative AI (GAI) models have the unparalleled ability to generate text, images, audio, and other forms of media that are increasingly indistinguishable from human-generated content. As these models often train on publicly available data, including copyrighted materials, art and other creative works, they inadvertently risk violating copyright and misappropriation of intellectual property (IP). Due to the rapid development of generative AI technology and pressing ethical considerations from stakeholders, protective mechanisms and techniques are emerging at a high pace but lack systematisation. In this paper, we study the concerns regarding the intellectual property rights of training data and specifically focus on the properties of generative models that enable misuse leading to potential IP violations. Then we propose a taxonomy that leads to a systematic review of technical solutions for safeguarding the data from intellectual property violations in GAI.

cs.CY↗

arXiv2023

Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and Attacks

The commercial use of Machine Learning (ML) is spreading; at the same time, ML models are becoming more complex and more expensive to train, which makes Intellectual Property Protection (IPP) of trained models a pressing issue. Unlike other domains that can build on a solid understanding of the threats, attacks and defenses available to protect their IP, the ML-related research in this regard is still very fragmented. This is also due to a missing unified view as well as a common taxonomy of these aspects. In this paper, we systematize our findings on IPP in ML, while focusing on threats and attacks identified and defenses proposed at the time of writing. We develop a comprehensive threat model for IP in ML, categorizing attacks and defenses within a unified and consolidated taxonomy, thus bridging research from both the ML and security communities.

cs.LG↗

arXiv2022

I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences

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 data collection, hyperparameter tuning, and model training. However, by giving their customers access to the (predictions of their) models, MLaaS providers endanger their intellectual property, such as sensitive training data, optimised hyperparameters, or learned model parameters. Adversaries can create a copy of the model with (almost) identical behavior using the the prediction labels only. While many variants of this attack have been described, only scattered defence strategies have been proposed, addressing isolated threats. This raises the necessity for a thorough systematisation of the field of model stealing, to arrive at a comprehensive understanding why these attacks are successful, and how they could be holistically defended against. We address this by categorising and comparing model stealing attacks, assessing their performance, and exploring corresponding defence techniques in different settings. We propose a taxonomy for attack and defence approaches, and provide guidelines on how to select the right attack or defence strategy based on the goal and available resources. Finally, we analyse which defences are rendered less effective by current attack strategies.

cs.LG↗

arXiv2021

The FeatureCloud AI Store for Federated Learning in Biomedicine and Beyond

Machine Learning (ML) and Artificial Intelligence (AI) have shown promising results in many areas and are driven by the increasing amount of available data. However, this data is often distributed across different institutions and cannot be shared due to privacy concerns. Privacy-preserving methods, such as Federated Learning (FL), allow for training ML models without sharing sensitive data, but their implementation is time-consuming and requires advanced programming skills. Here, we present the FeatureCloud AI Store for FL as an all-in-one platform for biomedical research and other applications. It removes large parts of this complexity for developers and end-users by providing an extensible AI Store with a collection of ready-to-use apps. We show that the federated apps produce similar results to centralized ML, scale well for a typical number of collaborators and can be combined with Secure Multiparty Computation (SMPC), thereby making FL algorithms safely and easily applicable in biomedical and clinical environments.

cs.LG↗

arXiv2020

Privacy-preserving Artificial Intelligence Techniques in Biomedicine

Artificial intelligence (AI) has been successfully applied in numerous scientific domains. In biomedicine, AI has already shown tremendous potential, e.g. in the interpretation of next-generation sequencing data and in the design of clinical decision support systems. However, training an AI model on sensitive data raises concerns about the privacy of individual participants. For example, summary statistics of a genome-wide association study can be used to determine the presence or absence of an individual in a given dataset. This considerable privacy risk has led to restrictions in accessing genomic and other biomedical data, which is detrimental for collaborative research and impedes scientific progress. Hence, there has been a substantial effort to develop AI methods that can learn from sensitive data while protecting individuals' privacy. This paper provides a structured overview of recent advances in privacy-preserving AI techniques in biomedicine. It places the most important state-of-the-art approaches within a unified taxonomy and discusses their strengths, limitations, and open problems. As the most promising direction, we suggest combining federated machine learning as a more scalable approach with other additional privacy preserving techniques. This would allow to merge the advantages to provide privacy guarantees in a distributed way for biomedical applications. Nonetheless, more research is necessary as hybrid approaches pose new challenges such as additional network or computation overhead.

cs.CR↗