• Publicationsclose
• 2013-2022close
• Conference object close
• DK close
• University of Southern Denmark Research Output close
• Transport Research close

Federated learning (FL) is becoming an increasingly popular machine learning paradigm in application scenarios where sensitive data available at various local sites cannot be shared due to privacy protection regulations. In FL, the sensitive data never leaves the local sites and only model parameters are shared with a global aggregator. Nonetheless, it has recently been shown that, under some circumstances, the private data can be reconstructed from the model parameters, which implies that data leakage can occur in FL. In this paper, we draw attention to another risk associated with FL: Even if federated algorithms are individually privacy-preserving, combining them into pipelines is not necessarily privacy-preserving. We provide a concrete example from genome-wide association studies, where the combination of federated principal component analysis and federated linear regression allows the aggregator to retrieve sensitive patient data by solving an instance of the multidimensional subset sum problem. This supports the increasing awareness in the field that, for FL to be truly privacy-preserving, measures have to be undertaken to protect against data leakage at the aggregator.

The social construction of gender through the design of technological artefacts, such as automobiles, motorcycles and domestic technologies, has received growing interest within feminist technology studies (FTS). Building on the extant FTS literature, in this research we explore how design of public transport (bus, minibus, metro) as a sociotechnical system shapes women's experiences of commute in their everyday lives. Drawing on empirical data that comes from interviews with 32 women, we focus on the complex entanglements of the women’s interactions (1) within the vehicle as a technological artefact with its layout, interior elements and technologies such as cameras, and (2) with other passengers (both men and women) and the driver. These entanglements constitute gendered experiences in public transport. Our findings specify the strategies women develop with concerns of (physical and social) personal space, safety, and travel hours in public transport; some of which have gained more prominence during the Covid-19 pandemic. We underline the diversity of these strategies depending on vehicle types, routes, and time of travel within which women negotiate the material and social interactions. We argue that such interactions can, and should, inspire all stakeholders for responsible innovation for inclusive and egalitarian public transport design.

The detection of malicious HTTP(S) requests is a pressing concern in cyber security, in particular given the proliferation of HTTP-based (micro-)service architectures. In addition to rule-based systems for known attacks, anomaly detection has been shown to be a promising approach for unknown (zero-day) attacks. This article extends existing work by integrating outlier explanations for individual requests into an end-to-end pipeline. These end-to-end explanations reflect the internal working of the pipeline. Empirically, we show that found explanations coincide with manually labelled explanations for identified outliers, allowing security professionals to quickly identify and understand malicious requests.