arXiv subjects

Jonas C. Ditz

Publications and source records attributed to Jonas C. Ditz.

3 recordsLinked to original sources

arXiv2025

Secure human oversight of AI: Threat modeling in a socio-technical context

Human oversight of AI is promoted as a safeguard against risks such as inaccurate outputs, system malfunctions, or violations of fundamental rights, and is mandated in regulation like the European AI Act. Yet debates on human oversight have largely focused on its effectiveness, while overlooking a critical dimension: the security of human oversight. We argue that human oversight creates a new attack surface within the safety, security, and accountability architecture of AI operations. Drawing on cybersecurity perspectives, we model human oversight as an IT application for the purpose of systematic threat modeling of the human oversight process. Threat modeling allows us to identify security risks within human oversight and points towards possible mitigation strategies. Our contributions are: (1) introducing a security perspective on human oversight, (2) offering researchers and practitioners guidance on how to approach their human oversight applications from a security point of view, and (3) providing a systematic overview of attack vectors and hardening strategies to enable secure human oversight of AI.

cs.CR↗

arXiv2023

Convolutional Motif Kernel Networks

Artificial neural networks show promising performance in detecting correlations within data that are associated with specific outcomes. However, the black-box nature of such models can hinder the knowledge advancement in research fields by obscuring the decision process and preventing scientist to fully conceptualize predicted outcomes. Furthermore, domain experts like healthcare providers need explainable predictions to assess whether a predicted outcome can be trusted in high stakes scenarios and to help them integrating a model into their own routine. Therefore, interpretable models play a crucial role for the incorporation of machine learning into high stakes scenarios like healthcare. In this paper we introduce Convolutional Motif Kernel Networks, a neural network architecture that involves learning a feature representation within a subspace of the reproducing kernel Hilbert space of the position-aware motif kernel function. The resulting model enables to directly interpret and evaluate prediction outcomes by providing a biologically and medically meaningful explanation without the need for additional post-hoc analysis. We show that our model is able to robustly learn on small datasets and reaches state-of-the-art performance on relevant healthcare prediction tasks. Our proposed method can be utilized on DNA and protein sequences. Furthermore, we show that the proposed method learns biologically meaningful concepts directly from data using an end-to-end learning scheme.

cs.LG↗

arXiv2023

COmic: Convolutional Kernel Networks for Interpretable End-to-End Learning on (Multi-)Omics Data

Motivation: The size of available omics datasets is steadily increasing with technological advancement in recent years. While this increase in sample size can be used to improve the performance of relevant prediction tasks in healthcare, models that are optimized for large datasets usually operate as black boxes. In high stakes scenarios, like healthcare, using a black-box model poses safety and security issues. Without an explanation about molecular factors and phenotypes that affected the prediction, healthcare providers are left with no choice but to blindly trust the models. We propose a new type of artificial neural network, named Convolutional Omics Kernel Network (COmic). By combining convolutional kernel networks with pathway-induced kernels, our method enables robust and interpretable end-to-end learning on omics datasets ranging in size from a few hundred to several hundreds of thousands of samples. Furthermore, COmic can be easily adapted to utilize multi-omics data. Results: We evaluated the performance capabilities of COmic on six different breast cancer cohorts. Additionally, we trained COmic models on multi-omics data using the METABRIC cohort. Our models performed either better or similar to competitors on both tasks. We show how the use of pathway-induced Laplacian kernels opens the black-box nature of neural networks and results in intrinsically interpretable models that eliminate the need for post-hoc explanation models.

q-bio.QM↗