Evaluating Architectural Safeguards For Uncertain Ai Black Box Components
Download Evaluating Architectural Safeguards For Uncertain Ai Black Box Components PDF/ePub or read online books in Mobi eBooks. Click Download or Read Online button to get Evaluating Architectural Safeguards For Uncertain Ai Black Box Components book now. This website allows unlimited access to, at the time of writing, more than 1.5 million titles, including hundreds of thousands of titles in various foreign languages.
Evaluating Architectural Safeguards for Uncertain AI Black-Box Components
Author: Scheerer, Max
language: en
Publisher: KIT Scientific Publishing
Release Date: 2023-10-23
Although tremendous progress has been made in Artificial Intelligence (AI), it entails new challenges. The growing complexity of learning tasks requires more complex AI components, which increasingly exhibit unreliable behaviour. In this book, we present a model-driven approach to model architectural safeguards for AI components and analyse their effect on the overall system reliability.
Context-based Access Control and Attack Modelling and Analysis
Author: Walter, Maximilian
language: en
Publisher: KIT Scientific Publishing
Release Date: 2024-07-03
This work introduces architectural security analyses for detecting access violations and attack paths in software architectures. It integrates access control policies and vulnerabilities, often analyzed separately, into a unified approach using software architecture models. Contributions include metamodels for access control and vulnerabilities, scenario-based analysis, and two attack analyses. Evaluation demonstrates high accuracy in identifying issues for secure system development.
A Reference Structure for Modular Model-based Analyses
Author: Koch, Sandro Giovanni
language: en
Publisher: KIT Scientific Publishing
Release Date: 2024-04-25
In this work, the authors analysed the co-dependency between models and analyses, particularly the structure and interdependence of artefacts and the feature-based decomposition and composition of model-based analyses. Their goal is to improve the maintainability of model-based analyses. They have investigated the co-dependency of Domain-specific Modelling Languages (DSMLs) and model-based analyses regarding evolvability, understandability, and reusability.