Search

Explainable Artificial Intelligence (XAI) aims to improve the transparency of machine learning (ML) pipelines. We systematize the increasingly growing (but fragmented) microcosm of studies that develop and utilize XAI methods for defensive and offensive cybersecurity tasks. We identify 3 cybersecurity stakeholders, i.e., model users, designers, and adversaries, who utilize XAI for 4 distinct objectives within an ML pipeline, namely 1) XAI-enabled user assistance, 2) XAI-enabled model verification, 3) explanation verification & robustness, and 4) offensive use of explanations. Our analysis of the literature indicates that many of the XAI applications are designed with little understanding of how they might be integrated into analyst workflows – user studies for explanation evaluation are conducted in only 14% of the cases. The security literature sometimes also fails to disentangle the role of the various stakeholders, e.g., by providing explanations to model users and designers while also exposing them to adversaries. Additionally, the role of model designers is particularly minimized in the security literature. To this end, we present an illustrative tutorial for model designers, demonstrating how XAI can help with model verification. We also discuss scenarios where interpretability by design may be a better alternative. The systematization and the tutorial enable us to challenge several assumptions, and present open problems that can help shape the future of XAI research within cybersecurity., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Cyber Security

Geometallurgy is an interdisciplinary research field concerned with the planning, monitoring, and optimisation of mineral resource extraction and beneficiation. Geometallurgy relies on a quantitative understanding of primary resource characteristics such as mineralogical composition and texture, the spatial distribution and variability of these characteristics, and how they interact with mining and beneficiation processes. Thus, ­geometallurgy requires accurate analytical data for resource characterisation and detailed models of orebody geology, mining and processing technologies, mineral economics, and the often-complex interactions between them. Here, we introduce the fundamental concepts relevant to the field, with particular emphasis on the current state-of-the-art and some notes on potential future developments

State machines models are models that simulate the behavior of discrete event systems, capable of representing systems such as software systems, network interactions, and control systems, and have been researched extensively. The nature of most learning algorithms however is the assumption that all data be available at the begining of the algorithm, and little research has been done in learning state machines from streaming data. In this paper, we want to close this gap further by presenting a generic method for learning state machines from data streams, as well as a merge heuristic that uses sketches to account for incomplete prefix trees. We implement our approach in an open-source state merging library and compare it with existing methods. We show the effectiveness of our approach with respect to run-time, memory consumption, and quality of results on a well known open dataset.State machines models are models that simulate the behavior of discrete event systems, capable of representing systems such as software systems, network interactions, and control systems, and have been researched extensively. The nature of most learning algorithms however is the assumption that all data be available at the begining of the algorithm, and little research has been done in learning state machines from streaming data. In this paper, we want to close this gap further by presenting a generic method for learning state machines from data streams, as well as a merge heuristic that uses sketches to account for incomplete prefix trees. We implement our approach in an open-source state merging library and compare it with existing methods. We show the effectiveness of our approach with respect to run-time, memory consumption, and quality of results on a well known open dataset., Cyber Security

Background: Sustainable production and consumption are two important issues, which mutually interact. Whereas individuals have little direct influence on the former, they can play a key role on the latter. This paper describes the subject matter of sustainable consumption and outlines its key features. It also describes some international initiatives in this field. Results: By means of an international survey, the study explores the emphasis given to sustainable consumption during the second wave of the COVID-19 pandemic, and the degree of preparedness in individuals to engage in the purchase of green and sustainably manufactured products. The main results indicate that the pandemic offered an opportunity to promote sustainable consumption; nevertheless, the pandemic alone cannot be regarded as a ‘game changer’ in this topic. Conclusions: Apart from an online survey with responses from 31 countries, which makes it one of the most representative studies on the topic, a logit model was used to analyse the main variables that affect the probability of pro-environmental consumption behaviour because of the COVID-19 pandemic. The paper lists some of the technological and social innovations that may be needed, so as to guide more sustainable consumption patterns in a post-pandemic world.