In the digital age, cyber-threats are a growing concern for individuals, businesses, and governments alike. These threats can range from data breaches and identity theft to large-scale attacks on critical infrastructure. The consequences of such attacks can be severe, leading to financial losses, threats to national security, and the loss of lives. This paper presents a holistic approach to increase the security of critical infrastructures. For that, we propose an open, self-configurable, and AI-based automated cyber-defense platform that runs on specifically hardened devices and own hardware, can be deeply embedded in critical infrastructures and provides full visibility on network, endpoints, and software. In this paper, starting from a thorough analysis of related work, we describe the vision of our SOVEREIGN platform in the form of an architecture, discuss individual building blocks, and evaluate it qualitatively with respect to our requirements.

The adoption of wearable technologies, such as smartwatches or wristbands, is rising. End-users expect to use all of their devices in an interconnected and seamless manner to conduct digital transactions, e.g., to pay or identify via their smartwatches, and not only via their smartphones. As sensitive transactions are usually protected by hardware-enforced isolation mechanisms, such as Trusted Execution Environments (TEEs), this brings new challenges of interconnecting TEEs to collaboratively conduct such transactions. We therefore propose MultiTEE, a distributed TEE architecture for heterogeneous device clusters, enabling secure data exchange and cooperation between TEEs. MultiTEE relies on lightweight, secure channels between TEEs, combined with remote attestation for the integrity verification of software stacks, as well as a memory-safe implementation. This enables an interface between Trusted Applications (TAs) of the distributed TEE similar to the interfaces of classic, single device TEEs. To demonstrate the feasibility of our solution, we built a Proof of Concept (PoC), partially implementing the upcoming European Digital Identity (EUDI) wallet to show the usage of heterogeneous device clusters for electronic identification. We evaluate our solution regarding performance and security.

Creating analysis reports on events published in open source news data is a tedious task when done manually. Due to the large-scale nature of news data, analysts, such as government officials, often spend unnecessary resources when trying to research news data on a specific topic. In this paper, we present an interactive system for unsupervised classification of news articles in a dynamic set of hierarchical labels. By providing users with explanations in the form of highlighted words, we enable them to quickly assess the relevance of an article to a particular topic. We also provide aggregated visualisations to detect emerging events and include several quality-of-life enhancements such as a source rating mechanism and report generation.

With more computing workloads being shifted to the cloud, verifying the integrity of remote software stacks through remote attestation becomes an increasingly important topic. During remote attestation, a prover provides attestation evidence to a verifier, backed by a hardware trust anchor. While generating this information, which is essentially a list of hashes, is easy, examining the trustworthiness of the overall platform based on the provided list of hashes without context is difficult. Furthermore, as different trust anchors use different formats, interaction between devices using different attestation technologies is a complex problem.

Rule-based approaches have proven to be an efficient and explainable method for knowledge base completion. Their predictive quality is on par with classic knowledge graph embedding models such as TransE or ComplEx, however, they cannot achieve the results of neural models proposed recently. The performance of a rule-based approach depends crucially on the solution of the rule aggregation problem, which is concerned with the computation of a score for a prediction that is generated by several rules. Within this paper, we propose a supervised approach to learn a reweighted confidence value for each rule to get an optimal explanation for the training set given a specific aggregation function. In particular, we apply our approach to two aggregation functions: We learn weights for a noisy-or multiplication and apply logistic regression, which computes the score of a prediction as a sum of these weights. Due to the simplicity of both models the final score is fully explainable. Our experimental results show that we can significantly improve the predictive quality of a rule-based approach. We compare our method with current state-of-the-art latent models that lack explainability, and achieve promising results.

Training and evaluating language models increasingly requires the construction of meta-datasets -- diverse collections of curated data with clear provenance. Natural language prompting has recently lead to improved zero-shot generalization by transforming existing, supervised datasets into a variety of novel instruction tuning tasks, highlighting the benefits of meta-dataset curation. While successful in general-domain text, translating these data-centric approaches to biomedical language modeling remains challenging, as labeled biomedical datasets are significantly underrepresented in popular data hubs. To address this challenge, we introduce BigBio a community library of 126+ biomedical NLP datasets, currently covering 13 task categories and 10+ languages. BigBio facilitates reproducible meta-dataset curation via programmatic access to datasets and their metadata, and is compatible with current platforms for prompt engineering and end-to-end few/zero shot language model evaluation. We discuss our process for task schema harmonization, data auditing, contribution guidelines, and outline two illustrative use cases: zero-shot evaluation of biomedical prompts and large-scale, multi-task learning. BigBio is an ongoing community effort and is available at https://github.com/bigscience-workshop/biomedical

SUMMARY: Machine learning algorithms for link prediction can be valuable tools for hypothesis generation. However, many current algorithms are black boxes or lack good user interfaces that could facilitate insight into why predictions are made. We present LinkExplorer, a software suite for predicting, explaining and exploring links in large biomedical knowledge graphs. LinkExplorer integrates our novel, rule-based link prediction engine SAFRAN, which was recently shown to outcompete other explainable algorithms and established black-box algorithms. Here, we demonstrate highly competitive evaluation results of our algorithm on multiple large biomedical knowledge graphs, and release a web interface that allows for interactive and intuitive exploration of predicted links and their explanations. AVAILABILITY AND IMPLEMENTATION: A publicly hosted instance, source code and further documentation can be found at https://github.com/OpenBioLink/Explorer. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

We live in a time when billions of IoT devices are being deployed and increasingly relied upon. This makes ensuring their availability and recoverability in case of a compromise a paramount goal. The large and rapidly growing number of deployed IoT devices make manual recovery impractical, especially if the devices are dispersed over a large area. Thus, there is a need for a reliable and scalable remote recovery mechanism that works even after attackers have taken full control over devices, possibly misusing them or trying to render them useless.

SUMMARY: Recently, novel machine-learning algorithms have shown potential for predicting undiscovered links in biomedical knowledge networks. However, dedicated benchmarks for measuring algorithmic progress have not yet emerged. With OpenBioLink, we introduce a large-scale, high-quality and highly challenging biomedical link prediction benchmark to transparently and reproducibly evaluate such algorithms. Furthermore, we present preliminary baseline evaluation results. AVAILABILITY AND IMPLEMENTATION: Source code and data are openly available at https://github.com/OpenBioLink/OpenBioLink. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.