Refine
Year of publication
Document type
- Conference Proceeding (33)
- Article (peer-reviewed) (4)
- Part of a Book (1)
Language
- English (38)
Is part of the Bibliography
- Yes (38)
Keywords
- Cloud computing (12)
- Security (11)
- Privacy (6)
- Audit (3)
- Biometrics (3)
- Computer architecture (3)
- Docker (3)
- Monitoring (3)
- Usability (3)
- Agents (2)
- Authentication (2)
- Authentication technologies (2)
- Cloud security (2)
- Container virtualization (2)
- Continuous authentication (2)
- Data privacy (2)
- Digital evidence (2)
- Digital forensics (2)
- Generative models (2)
- Hardware (2)
- IaaS (2)
- OSGi (2)
- Pix2Pix (2)
- System call tracing (2)
- Transparent authentication (2)
- User authentication (2)
- AAL (1)
- Access control (1)
- Access-control (1)
- Accountability (1)
- Ambient assisted living (1)
- Anomalous behavior (1)
- Anomalous behaviour (1)
- Artificial intelligence (1)
- Augmentation (1)
- Autonomous agents (1)
- Biological neural networks (1)
- Blockchain (1)
- Bounding-box regression (1)
- Business (1)
- CNN (1)
- Cloud (1)
- Cloud Computing (1)
- Cloud Customer (1)
- Cloud Forensics (1)
- Cloud Provider (1)
- Cloud audit (1)
- Cloud audits (1)
- Cloud forensic challenges (1)
- Cloud forensic solutions (1)
- Cloud forensics challenges (1)
- Cloud forensics solutions (1)
- Clouds (1)
- Container (1)
- Context aware (1)
- Cyber security (1)
- Cybersecurity (1)
- Data flow (1)
- Digital Forensics (1)
- Digital forensic (1)
- Digital investigation (1)
- Distance measurement (1)
- Distributed OSGi (1)
- Emergency-situations (1)
- Endoscopy (1)
- Explainable AI (1)
- FastCAM (1)
- Federated cloud (1)
- Federated identity (1)
- Forensic acquisition (1)
- Forensic analysis (1)
- Fuzzy control (1)
- Fuzzy logic (1)
- HPC (1)
- Healthcare (1)
- Hybrid Cloud (1)
- Hyperparameter tuning (1)
- Instance segmentation (1)
- Internet of things (1)
- Load Balancing (1)
- Load modeling (1)
- Machine learning (1)
- Mathematical model (1)
- Medical services (1)
- Metalworking (1)
- Meteorology (1)
- Metrics (1)
- Neural net-works (1)
- OSGi Service Architecture (1)
- Object detection (1)
- PaaS (1)
- PaaS Management (1)
- Peer-reviewed of the scientific committee (1)
- Poisoning (1)
- Prediction (1)
- QoS (1)
- Quality assessment (1)
- Quality of service (1)
- Reliability (1)
- SLA (1)
- SaaS (1)
- Security Audit as a Service (1)
- Security monitoring (1)
- Security policies (1)
- Single sign-on (1)
- Storage (1)
- Storage management (1)
- TAS (1)
- Time factors (1)
- Training (1)
- Trust (1)
- Universal image quality index (1)
- User survey (1)
- Users' perceptions (1)
- Users’ security practices (1)
- Verifiability (1)
- Virtual machining (1)
- Virtualization (1)
- XAI (1)
Software Defined Privacy
(2017)
Software Defined Privacy
(2016)
Explainable Artificial Intelligence (XAI) seeks to enhance transparency and trust in AI systems. Evaluating the quality of XAI explanation methods remains challenging due to limitations in existing metrics. To address these issues, we propose a novel metric called Explanation Significance Assessment (ESA) and its extension, the Weighted Explanation Significance Assessment (WESA). These metrics offer a comprehensive evaluation of XAI explanations, considering spatial precision, focus overlap, and relevance accuracy. In this paper, we demonstrate the applicability of ESA and WESA on medical data. These metrics quantify the understandability and reliability of XAI explanations, assisting practitioners in interpreting AI-based decisions and promoting informed choices in critical domains like healthcare. Moreover, ESA and WESA can play a crucial role in AI certification, ensuring both accuracy and explainability. By evaluating the performance of XAI methods and underlying AI models, these metrics contribute to trustworthy AI systems. Incorporating ESA and WESA in AI certification efforts advances the field of XAI and bridges the gap between accuracy and interpretability. In summary, ESA and WESA provide comprehensive metrics to evaluate XAI explanations, benefiting research, critical domains, and AI certification, thereby enabling trustworthy and interpretable AI systems.