004 Datenverarbeitung; Informatik
Refine
Year of publication
- 2021 (81) (remove)
Document Type
- Article (58)
- Conference Proceeding (8)
- Doctoral Thesis (7)
- Monograph/Edited Volume (6)
- Postprint (2)
Is part of the Bibliography
- yes (81) (remove)
Keywords
- blockchain (3)
- business process management (2)
- business processes (2)
- computer vision (2)
- cyber-physical systems (2)
- deferred choice (2)
- formal semantics (2)
- memory (2)
- oracles (2)
- perception of robots (2)
Institute
- Hasso-Plattner-Institut für Digital Engineering GmbH (23)
- Hasso-Plattner-Institut für Digital Engineering gGmbH (19)
- Institut für Informatik und Computational Science (11)
- Fachgruppe Betriebswirtschaftslehre (9)
- Bürgerliches Recht (4)
- Department Linguistik (3)
- Extern (3)
- Institut für Biochemie und Biologie (3)
- Department Erziehungswissenschaft (2)
- Institut für Physik und Astronomie (2)
In recent years, many efforts have been made to apply image processing techniques for plant leaf identification. However, categorizing leaf images at the cultivar/variety level, because of the very low inter-class variability, is still a challenging task. In this research, we propose an automatic discriminative method based on convolutional neural networks (CNNs) for classifying 12 different cultivars of common beans that belong to three various species. We show that employing advanced loss functions, such as Additive Angular Margin Loss and Large Margin Cosine Loss, instead of the standard softmax loss function for the classification can yield better discrimination between classes and thereby mitigate the problem of low inter-class variability. The method was evaluated by classifying species (level I), cultivars from the same species (level II), and cultivars from different species (level III), based on images from the leaf foreside and backside. The results indicate that the performance of the classification algorithm on the leaf backside image dataset is superior. The maximum mean classification accuracies of 95.86, 91.37 and 86.87% were obtained at the levels I, II and III, respectively. The proposed method outperforms the previous relevant works and provides a reliable approach for plant cultivars identification.
Dass Technologien wie Machine Learning-Anwendungen oder Big bzw. Smart Data- Verfahren unbedingt Daten in ausreichender Menge und Güte benötigen, erscheint inzwischen als Binsenweisheit. Vor diesem Hintergrund hat insbesondere der EU-Gesetzgeber für sich zuletzt ein neues Betätigungsfeld entdeckt, indem er versucht, auf unterschiedlichen Wegen Anreize zum Datenteilen zu schaffen, um Innovation zu kreieren. Hierzu zählt auch eine geradezu wohltönend mit ,,Datenaltruismus‘‘ verschlagwortete Konstellation. Der Beitrag stellt die diesbezüglichen Regulierungserwägungen auf supranationaler Ebene dar und nimmt eine erste Analyse vor.
Intrinsic decomposition refers to the problem of estimating scene characteristics, such as albedo and shading, when one view or multiple views of a scene are provided. The inverse problem setting, where multiple unknowns are solved given a single known pixel-value, is highly under-constrained. When provided with correlating image and depth data, intrinsic scene decomposition can be facilitated using depth-based priors, which nowadays is easy to acquire with high-end smartphones by utilizing their depth sensors. In this work, we present a system for intrinsic decomposition of RGB-D images on smartphones and the algorithmic as well as design choices therein. Unlike state-of-the-art methods that assume only diffuse reflectance, we consider both diffuse and specular pixels. For this purpose, we present a novel specularity extraction algorithm based on a multi-scale intensity decomposition and chroma inpainting. At this, the diffuse component is further decomposed into albedo and shading components. We use an inertial proximal algorithm for non-convex optimization (iPiano) to ensure albedo sparsity. Our GPU-based visual processing is implemented on iOS via the Metal API and enables interactive performance on an iPhone 11 Pro. Further, a qualitative evaluation shows that we are able to obtain high-quality outputs. Furthermore, our proposed approach for specularity removal outperforms state-of-the-art approaches for real-world images, while our albedo and shading layer decomposition is faster than the prior work at a comparable output quality. Manifold applications such as recoloring, retexturing, relighting, appearance editing, and stylization are shown, each using the intrinsic layers obtained with our method and/or the corresponding depth data.
Crochet is a popular handcraft all over the world. While other techniques such as knitting or weaving have received technical support over the years through machines, crochet is still a purely manual craft. Not just the act of crochet itself is manual but also the process of creating instructions for new crochet patterns, which is barely supported by domain specific digital solutions. This leads to unstructured and often also ambiguous and erroneous pattern instructions. In this report, we propose a concept to digitally represent crochet patterns. This format incorporates crochet techniques which allows domain specific support for crochet pattern designers during the pattern creation and instruction writing process. As contributions, we present a thorough domain analysis, the concept of a graph structure used as domain specific language to specify crochet patterns and a prototype of a projectional editor using the graph as representation format of patterns and a diagramming system to visualize them in 2D and 3D. By analyzing the domain, we learned about crochet techniques and pain points of designers in their pattern creation workflow. These insights are the basis on which we defined the pattern representation. In order to evaluate our concept, we built a prototype by which the feasibility of the concept is shown and we tested the software with professional crochet designers who approved of the concept.
Argument mining on twitter
(2021)
In the last decade, the field of argument mining has grown notably. However, only relatively few studies have investigated argumentation in social media and specifically on Twitter. Here, we provide the, to our knowledge, first critical in-depth survey of the state of the art in tweet-based argument mining. We discuss approaches to modelling the structure of arguments in the context of tweet corpus annotation, and we review current progress in the task of detecting argument components and their relations in tweets. We also survey the intersection of argument mining and stance detection, before we conclude with an outlook.
Cyber-physical systems often encompass complex concurrent behavior with timing constraints and probabilistic failures on demand. The analysis whether such systems with probabilistic timed behavior adhere to a given specification is essential. When the states of the system can be represented by graphs, the rule-based formalism of Probabilistic Timed Graph Transformation Systems (PTGTSs) can be used to suitably capture structure dynamics as well as probabilistic and timed behavior of the system. The model checking support for PTGTSs w.r.t. properties specified using Probabilistic Timed Computation Tree Logic (PTCTL) has been already presented. Moreover, for timed graph-based runtime monitoring, Metric Temporal Graph Logic (MTGL) has been developed for stating metric temporal properties on identified subgraphs and their structural changes over time. In this paper, we (a) extend MTGL to the Probabilistic Metric Temporal Graph Logic (PMTGL) by allowing for the specification of probabilistic properties, (b) adapt our MTGL satisfaction checking approach to PTGTSs, and (c) combine the approaches for PTCTL model checking and MTGL satisfaction checking to obtain a Bounded Model Checking (BMC) approach for PMTGL. In our evaluation, we apply an implementation of our BMC approach in AutoGraph to a running example.
We introduce a logic-based incremental approach to graph repair, generating a sound and complete (upon termination) overview of least-changing graph repairs from which a user may select a graph repair based on non-formalized further requirements. This incremental approach features delta preservation as it allows to restrict the generation of graph repairs to delta-preserving graph repairs, which do not revert the additions and deletions of the most recent consistency-violating graph update. We specify consistency of graphs using the logic of nested graph conditions, which is equivalent to first-order logic on graphs. Technically, the incremental approach encodes if and how the graph under repair satisfies a graph condition using the novel data structure of satisfaction trees, which are adapted incrementally according to the graph updates applied. In addition to the incremental approach, we also present two state-based graph repair algorithms, which restore consistency of a graph independent of the most recent graph update and which generate additional graph repairs using a global perspective on the graph under repair. We evaluate the developed algorithms using our prototypical implementation in the tool AutoGraph and illustrate our incremental approach using a case study from the graph database domain.
The automated detection of sequential anomalies in time series is an essential task for many applications, such as the monitoring of technical systems, fraud detection in high-frequency trading, or the early detection of disease symptoms. All these applications require the detection to find all sequential anomalies possibly fast on potentially very large time series. In other words, the detection needs to be effective, efficient and scalable w.r.t. the input size. Series2Graph is an effective solution based on graph embeddings that are robust against re-occurring anomalies and can discover sequential anomalies of arbitrary length and works without training data. Yet, Series2Graph is no t scalable due to its single-threaded approach; it cannot, in particular, process arbitrarily large sequences due to the memory constraints of a single machine. In this paper, we propose our distributed anomaly detection system, short DADS, which is an efficient and scalable adaptation of Series2Graph. Based on the actor programming model, DADS distributes the input time sequence, intermediate state and the computation to all processors of a cluster in a way that minimizes communication costs and synchronization barriers. Our evaluation shows that DADS is orders of magnitude faster than S2G, scales almost linearly with the number of processors in the cluster and can process much larger input sequences due to its scale-out property.
Analysis of protrusion dynamics in amoeboid cell motility by means of regularized contour flows
(2021)
Amoeboid cell motility is essential for a wide range of biological processes including wound healing, embryonic morphogenesis, and cancer metastasis. It relies on complex dynamical patterns of cell shape changes that pose long-standing challenges to mathematical modeling and raise a need for automated and reproducible approaches to extract quantitative morphological features from image sequences. Here, we introduce a theoretical framework and a computational method for obtaining smooth representations of the spatiotemporal contour dynamics from stacks of segmented microscopy images. Based on a Gaussian process regression we propose a one-parameter family of regularized contour flows that allows us to continuously track reference points (virtual markers) between successive cell contours. We use this approach to define a coordinate system on the moving cell boundary and to represent different local geometric quantities in this frame of reference. In particular, we introduce the local marker dispersion as a measure to identify localized membrane expansions and provide a fully automated way to extract the properties of such expansions, including their area and growth time. The methods are available as an open-source software package called AmoePy, a Python-based toolbox for analyzing amoeboid cell motility (based on time-lapse microscopy data), including a graphical user interface and detailed documentation. Due to the mathematical rigor of our framework, we envision it to be of use for the development of novel cell motility models. We mainly use experimental data of the social amoeba Dictyostelium discoideum to illustrate and validate our approach. <br /> Author summary Amoeboid motion is a crawling-like cell migration that plays an important key role in multiple biological processes such as wound healing and cancer metastasis. This type of cell motility results from expanding and simultaneously contracting parts of the cell membrane. From fluorescence images, we obtain a sequence of points, representing the cell membrane, for each time step. By using regression analysis on these sequences, we derive smooth representations, so-called contours, of the membrane. Since the number of measurements is discrete and often limited, the question is raised of how to link consecutive contours with each other. In this work, we present a novel mathematical framework in which these links are described by regularized flows allowing a certain degree of concentration or stretching of neighboring reference points on the same contour. This stretching rate, the so-called local dispersion, is used to identify expansions and contractions of the cell membrane providing a fully automated way of extracting properties of these cell shape changes. We applied our methods to time-lapse microscopy data of the social amoeba Dictyostelium discoideum.
Selbstbestimmtes Lernen mit Onlinekursen findet zunehmend mehr Akzeptanz in unserer Gesellschaft. Lernende können mithilfe von Onlinekursen selbst festlegen, was sie wann lernen und Kurse können durch vielfältige Adaptionen an den Lernfortschritt der Nutzer angepasst und individualisiert werden. Auf der einen Seite ist eine große Zielgruppe für diese Lernangebote vorhanden. Auf der anderen Seite sind die Erstellung von Onlinekursen, ihre Bereitstellung, Wartung und Betreuung kostenintensiv, wodurch hochwertige Angebote häufig kostenpflichtig angeboten werden müssen, um als Anbieter zumindest kostenneutral agieren zu können. In diesem Beitrag erörtern und diskutieren wir ein offenes, nachhaltiges datengetriebenes zweiseitiges Geschäftsmodell zur Verwertung geprüfter Onlinekurse und deren kostenfreie Bereitstellung für jeden Lernenden. Kern des Geschäftsmodells ist die Nutzung der dabei entstehenden Verhaltensdaten, die daraus mögliche Ableitung von Persönlichkeitsmerkmalen und Interessen und deren Nutzung im kommerziellen Kontext. Dies ist eine bei der Websuche bereits weitläufig akzeptierte Methode, welche nun auf den Lernkontext übertragen wird. Welche Möglichkeiten, Herausforderungen, aber auch Barrieren überwunden werden müssen, damit das Geschäftsmodell nachhaltig und ethisch vertretbar funktioniert, werden zwei unabhängige, jedoch synergetisch verbundene Geschäftsmodelle vorgestellt und diskutiert. Zusätzlich wurde die Akzeptanz und Erwartung der Zielgruppe für das vorgestellte Geschäftsmodell untersucht, um notwendige Kernressourcen für die Praxis abzuleiten. Die Ergebnisse der Untersuchung zeigen, dass das Geschäftsmodell von den Nutzer*innen grundlegend akzeptiert wird. 10 % der Befragten würden es bevorzugen, mit virtuellen Assistenten – anstelle mit Tutor*innen zu lernen. Zudem ist der Großteil der Nutzer*innen sich nicht darüber bewusst, dass Persönlichkeitsmerkmale anhand des Nutzerverhaltens abgeleitet werden können.
Learning analytics at scale
(2021)
Digital technologies are paving the way for innovative educational approaches. The learning format of Massive Open Online Courses (MOOCs) provides a highly accessible path to lifelong learning while being more affordable and flexible than face-to-face courses. Thereby, thousands of learners can enroll in courses mostly without admission restrictions, but this also raises challenges. Individual supervision by teachers is barely feasible, and learning persistence and success depend on students' self-regulatory skills. Here, technology provides the means for support. The use of data for decision-making is already transforming many fields, whereas in education, it is still a young research discipline. Learning Analytics (LA) is defined as the measurement, collection, analysis, and reporting of data about learners and their learning contexts with the purpose of understanding and improving learning and learning environments. The vast amount of data that MOOCs produce on the learning behavior and success of thousands of students provides the opportunity to study human learning and develop approaches addressing the demands of learners and teachers.
The overall purpose of this dissertation is to investigate the implementation of LA at the scale of MOOCs and to explore how data-driven technology can support learning and teaching in this context. To this end, several research prototypes have been iteratively developed for the HPI MOOC Platform. Hence, they were tested and evaluated in an authentic real-world learning environment. Most of the results can be applied on a conceptual level to other MOOC platforms as well. The research contribution of this thesis thus provides practical insights beyond what is theoretically possible. In total, four system components were developed and extended:
(1) The Learning Analytics Architecture: A technical infrastructure to collect, process, and analyze event-driven learning data based on schema-agnostic pipelining in a service-oriented MOOC platform. (2) The Learning Analytics Dashboard for Learners: A tool for data-driven support of self-regulated learning, in particular to enable learners to evaluate and plan their learning activities, progress, and success by themselves. (3) Personalized Learning Objectives: A set of features to better connect learners' success to their personal intentions based on selected learning objectives to offer guidance and align the provided data-driven insights about their learning progress. (4) The Learning Analytics Dashboard for Teachers: A tool supporting teachers with data-driven insights to enable the monitoring of their courses with thousands of learners, identify potential issues, and take informed action.
For all aspects examined in this dissertation, related research is presented, development processes and implementation concepts are explained, and evaluations are conducted in case studies. Among other findings, the usage of the learner dashboard in combination with personalized learning objectives demonstrated improved certification rates of 11.62% to 12.63%. Furthermore, it was observed that the teacher dashboard is a key tool and an integral part for teaching in MOOCs. In addition to the results and contributions, general limitations of the work are discussed—which altogether provide a solid foundation for practical implications and future research.
A core operator of evolutionary algorithms (EAs) is the mutation. Recently, much attention has been devoted to the study of mutation operators with dynamic and non-uniform mutation rates. Following up on this area of work, we propose a new mutation operator and analyze its performance on the (1 + 1) Evolutionary Algorithm (EA). Our analyses show that this mutation operator competes with pre-existing ones, when used by the (1 + 1) EA on classes of problems for which results on the other mutation operators are available. We show that the (1 + 1) EA using our mutation operator finds a (1/3)-approximation ratio on any non-negative submodular function in polynomial time. We also consider the problem of maximizing a symmetric submodular function under a single matroid constraint and show that the (1 + 1) EA using our operator finds a (1/3)-approximation within polynomial time. This performance matches that of combinatorial local search algorithms specifically designed to solve these problems and outperforms them with constant probability. Finally, we evaluate the performance of the (1 + 1) EA using our operator experimentally by considering two applications: (a) the maximum directed cut problem on real-world graphs of different origins, with up to 6.6 million vertices and 56 million edges and (b) the symmetric mutual information problem using a four month period air pollution data set. In comparison with uniform mutation and a recently proposed dynamic scheme, our operator comes out on top on these instances.
Data privacy is a very important issue. Especially in fields like medicine, it is paramount to abide by the existing privacy regulations to preserve patients' anonymity. However, data is required for research and training machine learning models that could help gain insight into complex correlations or personalised treatments that may otherwise stay undiscovered. Those models generally scale with the amount of data available, but the current situation often prohibits building large databases across sites. So it would be beneficial to be able to combine similar or related data from different sites all over the world while still preserving data privacy. Federated learning has been proposed as a solution for this, because it relies on the sharing of machine learning models, instead of the raw data itself. That means private data never leaves the site or device it was collected on. Federated learning is an emerging research area, and many domains have been identified for the application of those methods. This systematic literature review provides an extensive look at the concept of and research into federated learning and its applicability for confidential healthcare datasets.
I can see it in your eyes
(2021)
Over the past years, extensive research has been dedicated to developing robust platforms and data-driven dialog models to support long-term human-robot interactions. However, little is known about how people's perception of robots and engagement with them develop over time and how these can be accurately assessed through implicit and continuous measurement techniques. In this paper, we explore this by involving participants in three interaction sessions with multiple days of zero exposure in between. Each session consists of a joint task with a robot as well as two short social chats with it before and after the task. We measure participants' gaze patterns with a wearable eye-tracker and gauge their perception of the robot and engagement with it and the joint task using questionnaires. Results disclose that aversion of gaze in a social chat is an indicator of a robot's uncanniness and that the more people gaze at the robot in a joint task, the worse they perform. In contrast with most HRI literature, our results show that gaze toward an object of shared attention, rather than gaze toward a robotic partner, is the most meaningful predictor of engagement in a joint task. Furthermore, the analyses of gaze patterns in repeated interactions disclose that people's mutual gaze in a social chat develops congruently with their perceptions of the robot over time. These are key findings for the HRI community as they entail that gaze behavior can be used as an implicit measure of people's perception of robots in a social chat and of their engagement and task performance in a joint task.
Gene expression data provide the expression levels of tens of thousands of genes from several hundred samples. These data are analyzed to detect biomarkers that can be of prognostic or diagnostic use. Traditionally, biomarker detection for gene expression data is the task of gene selection. The vast number of genes is reduced to a few relevant ones that achieve the best performance for the respective use case. Traditional approaches select genes based on their statistical significance in the data set. This results in issues of robustness, redundancy and true biological relevance of the selected genes. Integrative analyses typically address these shortcomings by integrating multiple data artifacts from the same objects, e.g. gene expression and methylation data. When only gene expression data are available, integrative analyses instead use curated information on biological processes from public knowledge bases. With knowledge bases providing an ever-increasing amount of curated biological knowledge, such prior knowledge approaches become more powerful. This paper provides a thorough overview on the status quo of biomarker detection on gene expression data with prior biological knowledge. We discuss current shortcomings of traditional approaches, review recent external knowledge bases, provide a classification and qualitative comparison of existing prior knowledge approaches and discuss open challenges for this kind of gene selection.
Comprior
(2021)
Background
Reproducible benchmarking is important for assessing the effectiveness of novel feature selection approaches applied on gene expression data, especially for prior knowledge approaches that incorporate biological information from online knowledge bases. However, no full-fledged benchmarking system exists that is extensible, provides built-in feature selection approaches, and a comprehensive result assessment encompassing classification performance, robustness, and biological relevance. Moreover, the particular needs of prior knowledge feature selection approaches, i.e. uniform access to knowledge bases, are not addressed. As a consequence, prior knowledge approaches are not evaluated amongst each other, leaving open questions regarding their effectiveness.
Results
We present the Comprior benchmark tool, which facilitates the rapid development and effortless benchmarking of feature selection approaches, with a special focus on prior knowledge approaches. Comprior is extensible by custom approaches, offers built-in standard feature selection approaches, enables uniform access to multiple knowledge bases, and provides a customizable evaluation infrastructure to compare multiple feature selection approaches regarding their classification performance, robustness, runtime, and biological relevance.
Conclusion
Comprior allows reproducible benchmarking especially of prior knowledge approaches, which facilitates their applicability and for the first time enables a comprehensive assessment of their effectiveness
Background:
Research into the application of virtual reality technology in the health care sector has rapidly increased, resulting in a large body of research that is difficult to keep up with.
Objective:
We will provide an overview of the annual publication numbers in this field and the most productive and influential countries, journals, and authors, as well as the most used, most co-occurring, and most recent keywords.
Methods:
Based on a data set of 356 publications and 20,363 citations derived from Web of Science, we conducted a bibliometric analysis using BibExcel, HistCite, and VOSviewer.
Results:
The strongest growth in publications occurred in 2020, accounting for 29.49% of all publications so far. The most productive countries are the United States, the United Kingdom, and Spain; the most influential countries are the United States, Canada, and the United Kingdom. The most productive journals are the Journal of Medical Internet Research (JMIR), JMIR Serious Games, and the Games for Health Journal; the most influential journals are Patient Education and Counselling, Medical Education, and Quality of Life Research. The most productive authors are Riva, del Piccolo, and Schwebel; the most influential authors are Finset, del Piccolo, and Eide. The most frequently occurring keywords other than “virtual” and “reality” are “training,” “trial,” and “patients.” The most relevant research themes are communication, education, and novel treatments; the most recent research trends are fitness and exergames.
Conclusions:
The analysis shows that the field has left its infant state and its specialization is advancing, with a clear focus on patient usability.
Compound values are not universally supported in virtual machine (VM)-based programming systems and languages. However, providing data structures with value characteristics can be beneficial. On one hand, programming systems and languages can adequately represent physical quantities with compound values and avoid inconsistencies, for example, in representation of large numbers. On the other hand, just-in-time (JIT) compilers, which are often found in VMs, can rely on the fact that compound values are immutable, which is an important property in optimizing programs. Considering this, compound values have an optimization potential that can be put to use by implementing them in VMs in a way that is efficient in memory usage and execution time. Yet, optimized compound values in VMs face certain challenges: to maintain consistency, it should not be observable by the program whether compound values are represented in an optimized way by a VM; an optimization should take into account, that the usage of compound values can exhibit certain patterns at run-time; and that necessary value-incompatible properties due to implementation restrictions should be reduced.
We propose a technique to detect and compress common patterns of compound value usage at run-time to improve memory usage and execution speed. Our approach identifies patterns of frequent compound value references and introduces abbreviated forms for them. Thus, it is possible to store multiple inter-referenced compound values in an inlined memory representation, reducing the overhead of metadata and object references. We extend our approach by a notion of limited mutability, using cells that act as barriers for our approach and provide a location for shared, mutable access with the possibility of type specialization. We devise an extension to our approach that allows us to express automatic unboxing of boxed primitive data types in terms of our initial technique. We show that our approach is versatile enough to express another optimization technique that relies on values, such as Booleans, that are unique throughout a programming system. Furthermore, we demonstrate how to re-use learned usage patterns and optimizations across program runs, thus reducing the performance impact of pattern recognition.
We show in a best-case prototype that the implementation of our approach is feasible and can also be applied to general purpose programming systems, namely implementations of the Racket language and Squeak/Smalltalk. In several micro-benchmarks, we found that our approach can effectively reduce memory consumption and improve execution speed.
Empirical investigations on the uncanny valley have almost solely focused on the analysis of people?s noninteractive perception of a robot at first sight. Recent studies suggest, however, that these uncanny first impressions may be significantly altered over an interaction. What is yet to discover is whether certain interaction patterns can lead to a faster decline in uncanny feelings. In this paper, we present a study in which participants with limited expertise in Computer Science played a collaborative geography game with a Furhat robot. During the game, Furhat displayed one of two personalities, which corresponded to two different interaction strategies. The robot was either optimistic and encouraging, or impatient and provocative. We performed the study in a science museum and recruited participants among the visitors. Our findings suggest that a robot that is rated high on agreeableness, emotional stability, and conscientiousness can indeed weaken uncanny feelings. This study has important implications for human-robot interaction design as it further highlights that a first impression, merely based on a robot?s appearance, is not indicative of the affinity people might develop towards it throughout an interaction. We thus argue that future work should emphasize investigations on exact interaction patterns that can help to overcome uncanny feelings.
Bitcoin is gaining traction as an alternative store of value. Its market capitalization transcends all other cryptocurrencies in the market. But its high monetary value also makes it an attractive target to cyber criminal actors. Hacking campaigns usually target an ecosystem's weakest points. In Bitcoin, the exchange platforms are one of them. Each exchange breach is a threat not only to direct victims, but to the credibility of Bitcoin's entire ecosystem. Based on an extensive analysis of 36 breaches of Bitcoin exchanges, we show the attack patterns used to exploit Bitcoin exchange platforms using an industry standard for reporting intelligence on cyber security breaches. Based on this we are able to provide an overview of the most common attack vectors, showing that all except three hacks were possible due to relatively lax security. We show that while the security regimen of Bitcoin exchanges is subpar compared to other financial service providers, the use of stolen credentials, which does not require any hacking, is decreasing. We also show that the amount of BTC taken during a breach is decreasing, as well as the exchanges that terminate after being breached. Furthermore we show that overall security posture has improved, but still has major flaws. To discover adversarial methods post-breach, we have analyzed two cases of BTC laundering. Through this analysis we provide insight into how exchange platforms with lax cyber security even further increase the intermediary risk introduced by them into the Bitcoin ecosystem.