English
Related papers

Related papers: RISED: A Pre-Deployment Safety Evaluation Framewor…

200 papers

Legislation and public sentiment throughout the world have promoted fairness metrics, explainability, and interpretability as prescriptions for the responsible development of ethical artificial intelligence systems. Despite the importance…

Artificial Intelligence · Computer Science 2022-03-08 Erick Galinkin

Traditional cybersecurity methodologies target deterministic systems and fail to address the probabilistic nature of AI, leaving systems vulnerable to attack vectors such as model inversion, data poisoning, and prompt injection. Recent…

Cryptography and Security · Computer Science 2026-05-19 Tsafac Nkombong Regine Cyrille , Franziska Schwarz

Safety alignment in Large Language Models is critical for healthcare; however, reliance on binary refusal boundaries often results in \emph{over-refusal} of benign queries or \emph{unsafe compliance} with harmful ones. While existing…

Artificial Intelligence · Computer Science 2026-01-27 Zhihao Zhang , Liting Huang , Guanghao Wu , Preslav Nakov , Heng Ji , Usman Naseem

Artificial intelligence has transformed numerous industries, from healthcare to finance, enhancing decision-making through automated systems. However, the reliability of these systems is mainly dependent on the quality of the underlying…

Computers and Society · Computer Science 2025-06-04 Tadesse K. Bahiru , Haileleol Tibebu , Ioannis A. Kakadiaris

While Artificial Intelligence (AI) offers transformative potential for operational performance, its deployment in safety-critical domains such as aviation requires strict adherence to rigorous certification standards. Current EASA…

Artificial Intelligence · Computer Science 2026-04-03 Thomas Stefani , Johann Maximilian Christensen , Elena Hoemann , Frank Köster , Sven Hallerbach

Artificial intelligence (AI) systems, particularly those based on deep learning models, have increasingly achieved expert-level performance in medical applications. However, there is growing concern that such AI systems may reflect and…

Computation and Language · Computer Science 2025-04-25 Xiuying Chen , Tairan Wang , Juexiao Zhou , Zirui Song , Xin Gao , Xiangliang Zhang

Problem statement: Standardisation of AI fairness rules and benchmarks is challenging because AI fairness and other ethical requirements depend on multiple factors such as context, use case, type of the AI system, and so on. In this paper,…

Artificial Intelligence · Computer Science 2022-12-22 Avinash Agarwal , Harsh Agarwal

AI-readiness describes the degree to which data may be optimally and ethically used for subsequent AI and Machine Learning (AI/ML) methods, where those methods may involve some combination of model training, data classification, and…

Recent advances in clinical AI have enabled remarkable progress across many clinical domains. However, existing benchmarks and models are primarily limited to a small set of modalities and tasks, which hinders the development of large-scale…

Machine Learning · Computer Science 2025-03-21 Wei Dai , Peilin Chen , Malinda Lu , Daniel Li , Haowen Wei , Hejie Cui , Paul Pu Liang

Background: Artificial Intelligence (AI) clinical decision support (CDS) systems have the potential to augment surgical risk assessments, but successful adoption depends on an understanding of end-user needs and current workflows. This…

Human-Computer Interaction · Computer Science 2025-04-04 Andrea E Davidson , Jessica M Ray , Yulia Levites Strekalova , Parisa Rashidi , Azra Bihorac

Enterprise AI Assistants are increasingly deployed in domains where accuracy is paramount, making each erroneous output a potentially significant incident. This paper presents a comprehensive framework for monitoring, benchmarking, and…

Artificial Intelligence · Computer Science 2025-04-22 Akash V. Maharaj , David Arbour , Daniel Lee , Uttaran Bhattacharya , Anup Rao , Austin Zane , Avi Feller , Kun Qian , Yunyao Li

As the development of Large Models (LMs) progresses rapidly, their safety is also a priority. In current Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) safety workflow, evaluation, diagnosis, and alignment are…

There has been a prevalence of applying AI software in both high-stakes public-sector and industrial contexts. However, the lack of transparency has raised concerns about whether these data-informed AI software decisions secure fairness…

Machine Learning · Computer Science 2025-11-17 Xiaoyin Xi , Zhe Yu

Deep learning models have gained increasing adoption in medical image analysis. However, these models often produce overconfident predictions, which can compromise clinical accuracy and reliability. Bridging the gap between high-performance…

Image and Video Processing · Electrical Eng. & Systems 2026-03-24 Jutika Borah , Hidam Kumarjit Singh

Clinical personality assessment screens response validity before interpreting substantive scales. LLM evaluation does not. We apply the validity scaling framework from the PAI and MMPI-3 to metacognitive probe data from 20 frontier models…

Computation and Language · Computer Science 2026-04-21 Jon-Paul Cacioli

Prognostic and diagnostic AI-based medical devices hold immense promise for advancing healthcare, yet their rapid development has outpaced the establishment of appropriate validation methods. Existing approaches often fall short in…

Machine Learning · Computer Science 2024-09-10 Florian Hellmeier , Kay Brosien , Carsten Eickhoff , Alexander Meyer

This paper systematically derives design dimensions for the structured evaluation of explainable artificial intelligence (XAI) approaches. These dimensions enable a descriptive characterization, facilitating comparisons between different…

Human-Computer Interaction · Computer Science 2020-09-15 Fabian Sperrle , Mennatallah El-Assady , Grace Guo , Duen Horng Chau , Alex Endert , Daniel Keim

The applications of artificial intelligence (AI) are rapidly evolving, and they are also commonly used in safety-critical domains, such as autonomous driving and medical diagnosis, where functional safety is paramount. In AI-driven systems,…

Machine Learning · Computer Science 2024-05-12 Soyed Tuhin Ahmed , Michael Hefenbrock , Mehdi B. Tahoori

Large Reasoning Models (LRMs) and Multi-Agent Systems (MAS) in high-stakes domains demand reliable verification, yet centralized approaches suffer four limitations: (1) Robustness, with single points of failure vulnerable to attacks and…

Artificial Intelligence · Computer Science 2026-05-01 Yu-Chao Huang , Zhen Tan , Mohan Zhang , Pingzhi Li , Zhuo Zhang , Tianlong Chen