25 papers · ranked by Valyu relevance
Moritz Wäschle, Florian Thaler, Axel Berres, Florian Pölzlbauer + 1 more
'Albert Albers'] Remarkable progress in the fields of machine learning (ML) and artificial intelligence (AI) has led to an increased number of applications of (data-driven) AI systems for the partial or complete control of safety-critical systems. Recently, ML solutions have been particularly popular. Such approaches…
Jacqueline Harding, Cameron Domenico Kirk-Giannini
The field of AI safety seeks to prevent or reduce the harms caused by AI systems. A simple and appealing account of what is distinctive of AI safety as a field holds that this feature is constitutive: a research project falls within the purview of AI safety just in case it aims to prevent or reduce the harms caused by…
David Gros, Prémkumar Dévanbu, Yu Zhou
In this 4-page manuscript we discuss the problem of long-term AI Safety from a Software Engineering (SE) research viewpoint. We briefly summarize long-term AI Safety, and the challenge of avoiding harms from AI as systems meet or exceed human capabilities, including software engineering capabilities (and approach AGI /…
David Dalrymple, Joar Skalse, Yoshua Bengio, Stuart Russell + 13 more
AI Systems Authors: ['David Dalrymple' 'Joar Skalse' 'Yoshua Bengio' 'Stuart Russell' 'Max Tegmark' 'Sanjit A. Seshia' 'Steve Omohundro' 'Christian Szegedy' 'Ben Goldhaber' 'Nora Ammann' 'Alessandro Abate' 'Joe Halpern' 'Clark Barrett' 'Zhao Ding' 'Tan Zhi-Xuan' 'Jeannette M. Wing' 'Joshua B. Tenenbaum'] David…
Ibrahim Habli, Richard Hawkins, Colin Paterson, Philippa Ryan + 3 more
'Yan Jia' 'Mark Sujan' 'John McDermid'] IBRAHIM HABLI, Centre for Assuring Autonomy, University of York, United Kingdom RICHARD HAWKINS, Centre for Assuring Autonomy, University of York, United Kingdom COLIN PATERSON, Centre for Assuring Autonomy, University of York, United Kingdom PHILIPPA RYAN, Centre for Assuring…
Haoyu Gao, Mansooreh Zahedi, Wenxin Jiang, Hong Yi Lin + 2 more
Concerns, Practices, and Challenges Authors: ['Haoyu Gao' 'Mansooreh Zahedi' 'Wenxin Jiang' 'Hong Yi Lin' 'James C. Davis' 'Christoph Treude'] Many recent endeavours from the research community propose taxonomies of AI safety concerns [11, 29], evaluation methods [86], and mitigation approaches [43, 75, 90].…
Alice Pavaloiu, Utku Köse
Artificial Intelligence (AI) is an effective science which employs strong enough approaches, methods, and techniques to solve unsolvable real-world based problems. Because of its unstoppable rise towards the future, there are also some discussions about its ethics and safety. Shaping an AI-friendly environment for…
Elizabeth M. Borycki, Linda W. P. Peute, Femke van Sinderen, David Kaufman + 1 more
'David Kaufman' 'Andre W. Kushniruk'] Title: Summary Artificial intelligence (AI) promises to revolutionize healthcare. Currently there is a proliferation of new AI applications that are being developed and beginning to be deployed across many areas in healthcare to streamline and make healthcare processes more…
Dan Hendrycks, Mantas Mazeika, Thomas Woodside
Rapid advancements in artificial intelligence (AI) have sparked growing concerns among experts, policymakers, and world leaders regarding the potential for increasingly advanced AI systems to pose catastrophic risks. Although numerous risks have been detailed separately, there is a pressing need for a systematic…
Paul Festor, Yan Jia, Anthony C Gordon, A Aldo Faisal + 2 more
'Ibrahim Habli' 'Matthieu Komorowski'] Objectives Establishing confidence in the safety of Artificial Intelligence (AI)-based clinical decision support systems is important prior to clinical deployment and regulatory approval for systems with increasing autonomy. Here, we undertook safety assurance of the AI Clinician…
André Steimers, Moritz Schneider, Marc Wittlich, Massimo Esposito + 1 more
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. However, established risk mitigation measures in software development are only partially suitable for applications in AI systems…
Francesco Sovrano, Giulio Masetti
The AI Act has been recently proposed by the European Commission to regulate the use of AI in the EU, especially on high-risk applications, i.e. systems intended to be used as safety components in the management and operation of road traffic and the supply of water, gas, heating and electricity. On the other hand, IEC…
Meiyin Meng, Zaixi Zhang
Large language models (LLMs) are increasingly integrated into biomedical re-search workflows-from literature triage and hypothesis generation to experimental design-yet this expanded utility also heightens dual-use concerns, including the potential misuse for guiding toxic compound synthesis. In response, this study…
David C. Classen, Christopher Longhurst, Eric J. Thomas
This paper reviews the current state of patient safety and the application of artificial intelligence (AI) techniques to patient safety. This paper defines patient safety broadly, not just inpatient care but across the continuum of care, including diagnostic errors, misdiagnosis, adverse events, injuries, and…
Authors not listed
Realizing the promise of artificial intelligence (AI) to accelerate scientific progress and deliver technological impact depends on how effectively AI can be integrated into real-world decision- making processes. As Peter Norvig states, “Somewhat remarkably, almost all AI research until very recently has assumed that…
Cihan Tastan, Beyza Aydin
Chimeric antigen receptor T (CAR-T) cell therapy has achieved transformative success in hematological malignancies, yet its extension to solid tumors remains constrained by antigen heterogeneity, limited tumor infiltration, immunosuppressive tumor microenvironments, and on-target/off-tumor toxicity. Addressing these…
Xin Liu, Fan Fan
Translating preclinical safety findings into reliable insights for human risk assessment remains a fundamental challenge in drug development. Prior preclinical-clinical concordance studies have been constrained by limited drug coverage, reliance on identical-term matching for adverse events (AEs), and insufficient…
Yuta Matsubara, Hideki Tamura, Tetsuto Minami, Shigeki Nakauchi
The integration of mobile robots into human environments requires that they behave in trustworthy ways. Trust develops through interaction, and erratic movements can easily break it. Previous research examined motion predictability and smoothness separately, but their combined effect remains unclear. We investigated…
Authors not listed
Artificial intelligence (AI) is reshaping scientific research by accelerating discovery and enabling the analysis of complex data that traditional methods struggle to handle. This review examines over 310,000 journal articles and patents from the CAS Content Collection (2015–2025), with a focus on, biomedical research…
Authors not listed
Artificial intelligence (AI) is reshaping chemical engineering. Still, its role in safety-critical operations is limited because we rarely see tools that link physical models with data-driven methods. This study brings together three elements: physics-constrained neural networks, uncertainty quantification, and a…
Authors not listed
As the utilization of artificial intelligence (AI) and generative AI (GenAI) is expanding in the educational field, presenting significant implications for STEM disciplines, it is bringing opportunities to enhance how chemistry and chemical engineering are taught and learned. This perspective critically explores the…
A. Loy, M. Garafolj, H. Schauerte, H. Behnke + 4 more
We present a human-in-the-loop system for efficient rodent behavior analysis in drug development. Addressing the time-consuming and labor-intensive nature of manual behavior categorization, this UX-optimized platform integrates AI for complex behavior prediction and active learning to identify rare events. The proposed…
Jürgen Bajorath, Ana L. Chávez-Hernández, Miquel Duran-Frigola, Eli Fernández-de Gortari + 13 more
Jürgen Bajorath 2 , Ana L. Chávez-Hernández 1 , Miquel Duran-Frigola 3 , Eli Fernández-de Gortari 4 , Johann Gasteiger 5 , Edgar López-López1,6 , Gerald M. Maggiora 15 , José L. Medina-Franco 1 , Oscar Méndez-Lucio 7 , Jordi Mestres8,9 , Ramón Alain Miranda-Quintana 10 , Tudor I. Oprea 16 , Fabien Plisson 11 , Fernando…
Camilla Kao, Che-I Kao, Russell Furr
In science, safety can seem unfashionable. Satisfying safety requirements can slow the pace of research, make it cumbersome, or cost significant amounts of money. The logic of rules can seem unclear. Compliance can feel like a negative incentive. So besides the obvious benefit that safety keeps one safe, why do some…
Camilla Kao, Che-I Kao, Russell Furr
In science, safety can seem unfashionable. Satisfying safety requirements can slow the pace of research, make it cumbersome, or cost significant amounts of money. The logic of rules can seem unclear. Compliance can feel like a negative incentive. So besides the obvious benefit that safety keeps one safe, why do some…