paper-with-me

Papers

The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysis

2024-07-22 · Benjamin Fresz, Vincent Philipp Göbels, Safa Omri, Danilo Brajovic, Andreas Aichele, Janika Kutz, Jens Neuhüttler, Marco F. Huber

Developing and certifying safe - or so-called trustworthy - AI has become an increasingly salient issue, especially in light of upcoming regulation such as the EU AI Act. In this context, the black-box nature of machine learning models limits the use of conventional avenues of approach towards certifying complex technical systems. As a potential solution, methods to give insights into this black-box - devised in the field of eXplainable AI (XAI) - could be used. In this study, the potential and shortcomings of such methods for the purpose of safe AI development and certification are discussed in 15 qualitative interviews with experts out of the areas of (X)AI and certification. We find that XAI methods can be a helpful asset for safe AI development, as they can show biases and failures of ML-models, but since certification relies on comprehensive and correct information about technical systems, their impact is expected to be limited.

📄 PDF Abstract BibTeX arXiv:2408.02379

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Model Reporting for Certifiable AI: A Proposal from Merging EU Regulation into AI Development

2023-07-21 · Danilo Brajovic, Niclas Renner, Vincent Philipp Goebels, Philipp Wagner 외

Despite large progress in Explainable and Safe AI, practitioners suffer from a lack of regulation and standards for AI safety. In this work we merge recent regulation efforts by the European Union and first proposals for…

Document AI

Dynamic directed functional connectivity as a neural biomarker for objective motor skill assessment

2025-02-19 · Anil Kamat, Rahul Rahul, Anirban Dutta, Lora Cavuoto 외

Objective motor skill assessment plays a critical role in fields such as surgery, where proficiency is vital for certification and patient safety. Existing assessment methods, however, rely heavily on subjective human ju…

EEGFunctional ConnectivitySpecificity

CPS Engineering: Gap Analysis and Perspectives

2021-04-26 · Emmanuel Ledinot

Virtualization of computing and networking, IT-OT convergence, cybersecurity and AI-based enhancement of autonomy are significantly increasing the complexity of CPS and CPSoS. New challenges have emerged to demonstrate t…

RISC-V Functional Safety for Autonomous Automotive Systems: An Analytical Framework and Research Roadmap for ML-Assisted Certification

2026-04-19 · Nick Andreasyan, Mikhail Struve, Alexey Popov, Maksim Nikolaev 외 arxiv

RISC-V is emerging as a viable platform for automotive-grade embedded computing, with recent ISO 26262 ASIL-D certifications demonstrating readiness for safety-critical deployment in autonomous driving systems. However, …

Reinforcement LearningAutonomous Driving

Certification Labels for Trustworthy AI: Insights From an Empirical Mixed-Method Study

2023-05-15 · Nicolas Scharowski, Michaela Benk, Swen J. Kühne, Léane Wettstein 외

Auditing plays a pivotal role in the development of trustworthy AI. However, current research primarily focuses on creating auditable AI documentation, which is intended for regulators and experts rather than end-users a…

Survey