中文
相关论文

相关论文: A pragmatic classification framework for AI incide…

200 篇论文

Predictive process monitoring is concerned with the analysis of events produced during the execution of a process in order to predict the future state of ongoing cases thereof. Existing techniques in this field are able to predict, at each…

机器学习 · 计算机科学 2018-06-21 Irene Teinemaa , Niek Tax , Massimiliano de Leoni , Marlon Dumas , Fabrizio Maria Maggi

We outline the principles of classical assurance for computer-based systems that pose significant risks. We then consider application of these principles to systems that employ Artificial Intelligence (AI) and Machine Learning (ML). A key…

人工智能 · 计算机科学 2025-06-04 Robin Bloomfield , John Rushby

Detection of malicious activities in corporate environments is a very complex task and much effort has been invested into research of its automation. However, vast majority of existing methods operate only in a narrow scope which limits…

密码学与安全 · 计算机科学 2021-11-11 Jan Kohout , Čeněk Škarda , Kyrylo Shcherbin , Martin Kopp , Jan Brabec

The popularisation of applying AI in businesses poses significant challenges relating to ethical principles, governance, and legal compliance. Although businesses have embedded AI into their day-to-day processes, they lack a unified…

人工智能 · 计算机科学 2024-12-09 Haocheng Lin

Embedded into information systems, artificial intelligence (AI) faces security threats that exploit AI-specific vulnerabilities. This paper provides an accessible overview of adversarial attacks unique to predictive and generative AI…

密码学与安全 · 计算机科学 2025-07-01 Naoto Kiribuchi , Kengo Zenitani , Takayuki Semitsu

Automated control monitors could play an important role in overseeing highly capable AI agents that we do not fully trust. Prior work has explored control monitoring in simplified settings, but scaling monitoring to real-world deployments…

To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comprehensive assessment of their frontier risks. As Large…

Model monitoring involves analyzing AI algorithms once they have been deployed and detecting changes in their behaviour. This thesis explores machine learning model monitoring ML before the predictions impact real-world decisions or users.…

机器学习 · 计算机科学 2025-01-28 Carlos Mougan

Modern Security Operations Centers struggle with alert fatigue, fragmented tooling, and limited cross-source event correlation. Challenges that current Security Information Event Management and Extended Detection and Response systems only…

密码学与安全 · 计算机科学 2026-04-08 Anes Abdennebi , Nadjia Kara , Laaziz Lahlou , Hakima Ould-Slimane

This chapter introduces a conceptual framework for qualitative risk assessment of AI, particularly in the context of the EU AI Act. The framework addresses the complexities of legal compliance and fundamental rights protection by itegrating…

As artificial intelligence (AI) becomes increasingly embedded in digital, social, and institutional infrastructures, and AI and platforms are merged into hybrid structures, systemic risk has emerged as a critical but undertheorized…

计算机与社会 · 计算机科学 2026-05-26 Philipp Hacker , Lilian Edwards , Atoosa Kasirzadeh

High-risk industries like nuclear and aviation use real-time monitoring to detect dangerous system conditions. Similarly, Large Language Models (LLMs) need monitoring safeguards. We propose a real-time framework to predict harmful AI…

人工智能 · 计算机科学 2025-05-21 Maheep Chaudhary , Fazl Barez

The rapid advancement of ML models in critical sectors such as healthcare, finance, and security has intensified the need for robust data security, model integrity, and reliable outputs. Large multimodal foundational models, while crucial…

密码学与安全 · 计算机科学 2024-12-13 Hongyang Zhang , Yue Zhao , Claudio Angione , Harry Yang , James Buban , Ahmad Farhan , Fielding Johnston , Patrick Colangelo

A comprehensive approach to addressing catastrophic risks from AI models should cover the full model lifecycle. This paper explores contingency plans for cases where pre-deployment risk management falls short: where either very dangerous…

计算机与社会 · 计算机科学 2023-10-03 Joe O'Brien , Shaun Ee , Zoe Williams

We introduce a novel framework for human-AI collaboration in prediction and decision tasks. Our approach leverages human judgment to distinguish inputs which are algorithmically indistinguishable, or "look the same" to any feasible…

机器学习 · 计算机科学 2024-10-21 Rohan Alur , Loren Laine , Darrick K. Li , Dennis Shung , Manish Raghavan , Devavrat Shah

The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized…

计算与语言 · 计算机科学 2026-05-28 Katharina Deckenbach , Haritz Puerto , Jonas Geiping , Sahar Abdelnabi

The interaction between humans and AI in safety-critical systems presents a unique set of challenges that remain partially addressed by existing frameworks. These challenges stem from the complex interplay of requirements for transparency,…

In this work, we provide an industry research view for approaching the design, deployment, and operation of trustworthy Artificial Intelligence (AI) inference systems. Such systems provide customers with timely, informed, and customized…

The data available in the network traffic fromany Government building contains a significant amount ofinformation. An analysis of the traffic can yield insightsand situational understanding about what is happening inthe building. However,…

密码学与安全 · 计算机科学 2019-10-15 D. Verma , S. Calo

Vulnerability of Frontier language models to misuse and jailbreaks has prompted the development of safety measures like filters and alignment training in an effort to ensure safety through robustness to adversarially crafted prompts. We…

密码学与安全 · 计算机科学 2024-10-31 David Glukhov , Ziwen Han , Ilia Shumailov , Vardan Papyan , Nicolas Papernot