A5005216969- Blockchain Technology Applications and Security
- Logic, programming, and type systems
- Privacy-Preserving Technologies in Data
- Advanced Software Engineering Methodologies
- Model-Driven Software Engineering Techniques
- Software Engineering Research
- Cryptography and Data Security
- Artificial Intelligence in Healthcare and Education
- Mobile Crowdsensing and Crowdsourcing
- Formal Methods in Verification
- Distributed systems and fault tolerance
- Auction Theory and Applications
- Access Control and Trust
- Service-Oriented Architecture and Web Services
- Ethics and Social Impacts of AI
- Business Process Modeling and Analysis
- Cloud Computing and Resource Management
- Cloud Data Security Solutions
- Information and Cyber Security
- Semantic Web and Ontologies
- Natural Language Processing Techniques
- Software-Defined Networks and 5G
- IoT and Edge/Fog Computing
- Adversarial Robustness in Machine Learning
- Cardiac Arrest and Resuscitation
University of Copenhagen
2017-2024
TU Dortmund University
2012-2016
The ethical and societal implications of artificial intelligence systems raise concerns. In this article, we outline a novel process based on applied ethics, namely, Z-Inspection <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">®</sup> , to assess if an AI system is trustworthy. We use the definition trustworthy given by high-level European Commission's expert group AI. general inspection that can be variety domains where are used, such as...
This paper documents how an ethically aligned co-design methodology ensures trustworthiness in the early design phase of artificial intelligence (AI) system component for healthcare. The explains decisions made by deep learning networks analyzing images skin lesions. trustworthy AI developed here used a holistic approach rather than static ethical checklist and required multidisciplinary team experts working with designers their managers. Ethical, legal, technical issues potentially arising...
Artificial Intelligence (AI) has the potential to greatly improve delivery of healthcare and other services that advance population health wellbeing. However, use AI in also brings risks may cause unintended harm. To guide future developments AI, High-Level Expert Group on set up by European Commission (EC), recently published ethics guidelines for what it terms “trustworthy” AI. These are aimed at a variety stakeholders, especially guiding practitioners toward more ethical robust...
Managing and verifying forest products in a value chain is often reliant on easily manipulated document or digital tracking methods – Chain of Custody Systems. We aim to create new means timber by developing tamper proof system based Blockchain technology. will be combined with protocols for physical verification authentication. Deliverables include online traceability system, procedures entering data inputs. Certification schemes governments gain increased legitimacy from tamper-proof...
Abstract Building artificial intelligence (AI) systems that adhere to ethical standards is a complex problem. Even though multitude of guidelines for the design and development such trustworthy AI exist, these focus on high-level abstract requirements systems, it often very difficult assess if specific system fulfills requirements. The Z-Inspection® process provides holistic dynamic framework evaluate trustworthiness at different stages lifecycle, including intended use, design, development....
The ubiquity of crowdsourcing has reshaped the static sensor-enabled data sensing paradigm with cost efficiency and flexibility. Still, most existing triangular systems only work under centralized trust assumption suffer from various attacks mounted by malicious users. Although incorporating emerging blockchain technology into provides a possibility to mitigate some issues, how concretely implement crucial components their functionalities in verifiable privacy-aware manner remains...
Privacy-aware task allocation/matching has been an active research focus in crowdsourcing. However, existing studies on honest-but-curious assumption and a single-attribute matching model. There is lack of adequate attention paid to scheme designs against malicious behaviors supporting user-side personalized over multiple attributes. A few recent works employ blockchain cryptographic techniques decentralize the procedure with verifiable privacy-preserving on-chain executions. they still bear...
The early development of blockchain technology (BCT) has already demonstrated the technology's potential to serve needs different industries. BCT also become established as a popular research topic in scientific disciplines. This paper aims at introducing how several relevant disciplines—supply chain management; management, economics and finance; computer science; security engineering—see education perspectives for BCT. A field review is conducted present challenges opportunities BCT, well...
Blockchain and distributed ledger technology (BC/DLT) provides databases with decentralized governance, tamper-proof recording, high availability non-copyable digital assets, which have made it a natural technological basis for supply chain management. In this paper, we introduce REALISTIC, novel event-based modeling framework networks (SCNs) that includes production processes . It extends McCarty’s Resources-Events-Agents (REA) accounting model secure transformations , which, across the...
In combinatory logic one usually assumes a fixed set of basic combinators (axiom schemes), K and S. this setting the provable formulas (inhabited types) is PSPACE-complete in simple types undecidable intersection types. When arbitrary sets axiom schemes are considered, inhabitation problem even (this known as Linial-Post theorem). k-bounded with arises from by imposing bound k on depth (formulae) which may be substituted for type variables schemes. We consider (provability) k-bounded...
Sharding is a critical technique that enhances the scalability of blockchain technology.However, existing protocols often assume adversarial nodes in general term without considering different types attacks, which limits transaction throughput at runtime because attacks on liveness could be mitigated.There have been attempts to increase by separately handling attacks; however, they security vulnerabilities.This paper introduces Reticulum, novel sharding protocol overcomes these limitations...
This report is a methodological reflection on Z-Inspection$^{\small{\circledR}}$. Z-Inspection$^{\small{\circledR}}$ holistic process used to evaluate the trustworthiness of AI-based technologies at different stages AI lifecycle. It focuses, in particular, identification and discussion ethical issues tensions through elaboration socio-technical scenarios. uses general European Union's High-Level Expert Group's (EU HLEG) guidelines for trustworthy AI. illustrates both researchers...
Blockchain sharding splits a blockchain into several shards where consensus is reached at the shard level rather than over entire blockchain. It improves transaction throughput and reduces computational resources required of individual nodes. But derivation trustworthy within becomes an issue as longest chain based mechanisms used in conventional blockchains can no longer be used. Instead, vote-based mechanism must employed. However, existing Byzantine fault tolerance protocols do not offer...
For many software engineers, object-oriented frameworks represent the highest level of achievement in extensible design. The framework designers become experts a specific application domain and design cooperating classes that impose responsibilities collaborations for those seeking to extend framework. In short, once matures, it has complicated usage patterns must be followed otherwise nothing works. Turning into product line is challenging because difficulty coding these complex behaviors...
Blockchain sharding protocols randomly distribute nodes to different shards. They limit the quantity of shards ensure that adversary remains a minority inside each shard with high probability. There can exist only small number In this article, we propose new protocol links population in real-time instead fixed upper-bounded population. The is two-phase design. First, several committee are constructed where majority honest probability; then, splits into worker likelihood at least one node...