Ai alignment: A comprehensive survey

J Ji, T Qiu, B Chen, B Zhang, H Lou, K Wang… - arXiv preprint arXiv …, 2023 - arxiv.org
AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, the potential large-scale risks associated with misaligned AI …

Ethics-based AI auditing: A systematic literature review on conceptualizations of ethical principles and knowledge contributions to stakeholders

J Laine, M Minkkinen, M Mäntymäki - Information & Management, 2024 - Elsevier
This systematic literature review synthesizes the conceptualizations of ethical principles in AI
auditing literature and the knowledge contributions to the stakeholders of AI auditing. We …

[HTML][HTML] Rationalization for explainable nlp: A survey

S Gurrapu, A Kulkarni, L Huang… - Frontiers in Artificial …, 2023 - ncbi.nlm.nih.gov
Recent advances in deep learning have improved the performance of many Natural
Language Processing (NLP) tasks such as translation, question-answering, and text …

[HTML][HTML] Financial risk management and explainable, trustworthy, responsible AI

S Fritz-Morgenthal, B Hein… - Frontiers in artificial …, 2022 - frontiersin.org
This perspective paper is based on several sessions by the members of the Round Table AI
at FIRM, with input from a number of external and international speakers. Its particular focus …

[HTML][HTML] Sources of risk of AI systems

A Steimers, M Schneider - … Journal of Environmental Research and Public …, 2022 - mdpi.com
Artificial intelligence can be used to realise new types of protective devices and assistance
systems, so their importance for occupational safety and health is continuously increasing …

[HTML][HTML] Artificial intelligence risks and challenges in the Spanish public administration: An exploratory analysis through expert judgements

I Sobrino-García - Administrative Sciences, 2021 - mdpi.com
The expanding use of artificial intelligence (AI) in public administration is generating
numerous opportunities for governments. Current Spanish regulations have established …

Artificial Intelligence or Augmented Intelligence? Impact on our lives, rights and ethics

F De Felice, A Petrillo, C De Luca, I Baffo - Procedia Computer Science, 2022 - Elsevier
Artificial Intelligence (AI) is a highly topical issue that opens up opportunities still largely
unexplored, but also many economic, ethical and social issues. Questions about AI are …

Deep H2O: Cyber attacks detection in water distribution systems using deep learning

MNK Sikder, MBT Nguyen, ED Elliott… - Journal of Water Process …, 2023 - Elsevier
Abstract Water Distribution Systems (WDSs) leverage the recent technological
advancements in sensor technologies and Cyber-Physical Systems (CPSs) for better …

Outlier detection using AI: a survey

MNK Sikder, FA Batarseh - AI Assurance, 2023 - Elsevier
An outlier is an event or observation that is defined as an unusual activity, intrusion, or a
suspicious data point that lies at an irregular distance from a population. The definition of an …

[HTML][HTML] Enabling artificial intelligence adoption through assurance

L Freeman, A Rahman, FA Batarseh - Social Sciences, 2021 - mdpi.com
The wide scale adoption of Artificial Intelligence (AI) will require that AI engineers and
developers can provide assurances to the user base that an algorithm will perform as …