中文
相关论文

相关论文: A Survey on Failure Analysis and Fault Injection i…

200 篇论文

In this work, we present and analyze reported failures of artificially intelligent systems and extrapolate our analysis to future AIs. We suggest that both the frequency and the seriousness of future AI failures will steadily increase. AI…

人工智能 · 计算机科学 2016-10-26 Roman V. Yampolskiy , M. S. Spellchecker

Embodied AI systems, including robots and autonomous vehicles, are increasingly integrated into real-world applications, where they encounter a range of vulnerabilities stemming from both environmental and system-level factors. These…

密码学与安全 · 计算机科学 2025-02-26 Wenpeng Xing , Minghao Li , Mohan Li , Meng Han

Frontier AI systems are being adopted across Africa, yet most AI safety evaluations are designed and validated in Western environments. In this paper, we argue that the portability gap can leave Africa-centric pathways to severe harm…

As AI systems become integral to critical operations across industries and services, ensuring their reliability and safety is essential. We offer a framework that integrates established reliability and resilience engineering principles into…

人工智能 · 计算机科学 2024-11-15 Saurabh Mishra , Anand Rao , Ramayya Krishnan , Bilal Ayyub , Amin Aria , Enrico Zio

Fraud is a prevalent offence that extends beyond financial loss, causing psychological and physical harm to victims. The advancements in online communication technologies alowed for online fraud to thrive in this vast network, with…

AI-powered language learning tools increasingly provide instant, personalised feedback to millions of learners worldwide. However, this feedback can fail in ways that are difficult for learners--and even teachers--to detect, potentially…

人机交互 · 计算机科学 2026-05-25 Ben Knight , Wm. Matthew Kennedy , Danielle Carvalho , Isaac Pattis , James Edgell

Artificial Intelligence (AI) and, in particular, Machine Learning (ML) have emerged to be utilized in various applications due to their capability to learn how to solve complex problems. Over the last decade, rapid advances in ML have…

机器学习 · 计算机科学 2023-05-11 Mohammad Hasan Ahmadilivani , Mahdi Taheri , Jaan Raik , Masoud Daneshtalab , Maksim Jenihhin

AI scientist systems, capable of autonomously executing the full research workflow from hypothesis generation and experimentation to paper writing, hold significant potential for accelerating scientific discovery. However, the internal…

人工智能 · 计算机科学 2025-12-23 Ziming Luo , Atoosa Kasirzadeh , Nihar B. Shah

Federated learning (FL), as an emerging artificial intelligence (AI) approach, enables decentralized model training across multiple devices without exposing their local training data. FL has been increasingly gaining popularity in both…

The growing application of deep neural networks in safety-critical domains makes the analysis of faults that occur in such systems of enormous importance. In this paper we introduce a large taxonomy of faults in deep learning (DL) systems.…

软件工程 · 计算机科学 2019-11-11 Nargiz Humbatova , Gunel Jahangirova , Gabriele Bavota , Vincenzo Riccio , Andrea Stocco , Paolo Tonella

This chapter bridges technical analysis and organizational preparedness by tracing the path from layered failure modes to reliability awareness in generative and agentic AI systems. We first introduce an 11-layer failure stack, a structured…

系统与控制 · 电气工程与系统科学 2025-11-11 Janet , Lin , Liangwei Zhang

AI has become integral to safety-critical areas like autonomous driving systems (ADS) and robotics. The architecture of recent autonomous systems are trending toward end-to-end (E2E) monolithic architectures such as large language models…

人工智能 · 计算机科学 2025-07-24 Mandar Pitale , Jelena Frtunikj , Abhinaw Priyadershi , Vasu Singh , Maria Spence

Trusted Execution Environments (TEEs) are critical components of modern secure computing, providing isolated zones in processors to safeguard sensitive data and execute secure operations. Despite their importance, TEEs are increasingly…

密码学与安全 · 计算机科学 2024-11-25 Aaron Joy , Ben Soh , Zhi Zhang , Sri Parameswaran , Darshana Jayasinghe

The rapid growth of artificial intelligence (AI) technologies has raised major privacy and ethical concerns. However, existing AI incident taxonomies and guidelines lack grounding in real-world cases, limiting their effectiveness for…

计算机与社会 · 计算机科学 2025-09-22 Hilda Hadan , Reza Hadi Mogavi , Leah Zhang-Kennedy , Lennart E. Nacke

Artificial intelligence (AI) systems are being readily and rapidly adopted, increasingly permeating critical domains: from consumer platforms and enterprise software to networked systems with embedded agents. While this has unlocked…

密码学与安全 · 计算机科学 2025-12-16 Amy Chang , Tiffany Saade , Sanket Mendapara , Adam Swanda , Ankit Garg

While certain industrial sectors (e.g., aviation) have a long history of mandatory incident reporting complete with analytical findings, the practice of artificial intelligence (AI) safety benefits from no such mandate and thus analyses…

人工智能 · 计算机科学 2022-11-15 Nikiforos Pittaras , Sean McGregor

Despite the transformative impact of Artificial Intelligence (AI) across various sectors, cyber security continues to rely on traditional static and dynamic analysis tools, hampered by high false positive rates and superficial code…

密码学与安全 · 计算机科学 2025-04-28 Rajesh Yarra

Deep Learning (DL) has been widely adopted in diverse industrial domains, including autonomous driving, intelligent healthcare, and aided programming. Like traditional software, DL systems are also prone to faults, whose malfunctioning may…

机器学习 · 计算机科学 2026-01-01 Hanmo You , Zan Wang , Zishuo Dong , Luanqi Mo , Jianjun Zhao , Junjie Chen