Cybersecurity for AI systems: A survey

RS Sangwan, Y Badr, SM Srinivasan - Journal of Cybersecurity and …, 2023 - mdpi.com
Recent advances in machine learning have created an opportunity to embed artificial
intelligence in software-intensive systems. These artificial intelligence systems, however …

Evaluating the Reliability of Machine-Learning-based Predictions used in Nuclear Power Plant Instrumentation and Control Systems

E Chen, H Bao, N Dinh - Reliability Engineering & System Safety, 2024 - Elsevier
The field of data-driven, neural-network-based machine learning (ML) has seen significant
growth, with applications in various information and control systems. Despite promising real …

The Impact of Artificial Intelligence on Future Aviation Safety Culture

B Kirwan - Future Transportation, 2024 - mdpi.com
Artificial intelligence is developing at a rapid pace, with examples of machine learning
already being used in aviation to improve efficiency. In the coming decade, it is likely that …

On the robustness of dataset inference

S Szyller, R Zhang, J Liu, N Asokan - arXiv preprint arXiv:2210.13631, 2022 - arxiv.org
Machine learning (ML) models are costly to train as they can require a significant amount of
data, computational resources and technical expertise. Thus, they constitute valuable …

Reliability assurance for AI systems

JC Blood, NW Herbert… - 2023 Annual Reliability …, 2023 - ieeexplore.ieee.org
SUMMARY & CONCLUSIONSMany applications of artificial intelligence (AI)/assistive
automation are in the Army's pipeline of developmental technologies and systems. Ensuring …

Vulnerabilities in artificial intelligence and machine learning applications and data

SL Eggers, C Sample - 2020 - osti.gov
Artificial intelligence (AI) applications driven by machine learning (ML) are transformational
technologies within the international nuclear security regime. Advancements realized by AI …

Ownership and Confidentiality in Machine Learning

S Szyller - 2023 - aaltodoc.aalto.fi
Statistical and machine learning (ML) models have been the primary tools for data-driven
analysis for decades. Recent theoretical progress in deep neural networks (DNNs) coupled …

Towards logical specification of adversarial examples in machine learning

M Zeroual, B Hamid, M Adedjoumaa… - … Conference on Trust …, 2022 - ieeexplore.ieee.org
The use of Artificial Intelligence (AI)-based systems, using particularly Machine Learning
(ML) classifiers, is growing rapidly and finding uses in many industries. Most of these …

[PDF][PDF] Academics, AI, and APTs

D Cary - 2021 - pdfs.semanticscholar.org
Turning cutting-edge research into operational capabilities is the currency of cyber
operations. The vulnerability no one else knows about, one found by someone with highly …

AI Vulnerability, National Security, and Private Sector Power: Securitization theory meets AI

M Livingston - 2022 - papers.ssrn.com
Securing against AI vulnerabilities has rapidly risen to attention in US policy. AI systems are
vulnerable to attack and unintentional failure. While there have yet to be catastrophic …