中文
相关论文

相关论文: Relativistic Conceptions of Trustworthiness: Impli…

200 篇论文

AI systems are increasingly tasked to complete responsibilities with decreasing oversight. This delegation requires users to accept certain risks, typically mitigated by perceived or actual alignment of values between humans and AI, leading…

计算机与社会 · 计算机科学 2025-01-29 Jennifer Chien , David Danks

As Autonomous Systems (AS) become more ubiquitous in society, more responsible for our safety and our interaction with them more frequent, it is essential that they are trustworthy. Assessing the trustworthiness of AS is a mandatory…

人工智能 · 计算机科学 2023-05-12 Gregory Chance , Dhaminda B. Abeywickrama , Beckett LeClair , Owen Kerr , Kerstin Eder

Recommender systems (RSs) aim to help users to effectively retrieve items of their interests from a large catalogue. For a quite long period of time, researchers and practitioners have been focusing on developing accurate RSs. Recent years…

信息检索 · 计算机科学 2023-11-20 Shoujin Wang , Xiuzhen Zhang , Yan Wang , Huan Liu , Francesco Ricci

Artificial Intelligence (AI) technology epitomizes the complex challenges posed by human-made artifacts, particularly those widely integrated into society and exerting significant influence, highlighting potential benefits and their…

人工智能 · 计算机科学 2025-10-06 Michael Papademas , Xenia Ziouvelou , Antonis Troumpoukis , Vangelis Karkaletsis

Trustworthy AI encompasses many aspirational aspects for aligning AI systems with human values, including fairness, privacy, robustness, explainability, and uncertainty quantification. Ultimately the goal of Trustworthy AI research is to…

机器学习 · 计算机科学 2025-11-04 Jesse C. Cresswell

A common practice of ML systems development concerns the training of the same model under different data sets, and the use of the same (training and test) sets for different learning models. The first case is a desirable practice for…

计算机科学中的逻辑 · 计算机科学 2025-06-06 Leonardo Ceragioli , Giuseppe Primiero

Recently, requirements for the explainability of software systems have gained prominence. One of the primary motivators for such requirements is that explainability is expected to facilitate stakeholders' trust in a system. Although this…

软件工程 · 计算机科学 2021-08-16 Lena Kästner , Markus Langer , Veronika Lazar , Astrid Schomäcker , Timo Speith , Sarah Sterz

Trustworthiness and trust are basic factors in common societies that allow us to interact and enjoy being in crowds without fear. As robotic devices start percolating into our daily lives they must behave as fully trustworthy objects, such…

计算机与社会 · 计算机科学 2025-04-15 Gerhard P. Fettweis , Patricia Grünberg , Tim Hentschel , Stefan Köpsell

Recommender systems (RS), serving at the forefront of Human-centered AI, are widely deployed in almost every corner of the web and facilitate the human decision-making process. However, despite their enormous capabilities and potential, RS…

信息检索 · 计算机科学 2024-02-23 Yingqiang Ge , Shuchang Liu , Zuohui Fu , Juntao Tan , Zelong Li , Shuyuan Xu , Yunqi Li , Yikun Xian , Yongfeng Zhang

With growing concerns regarding bias and discrimination in predictive models, the AI community has increasingly focused on assessing AI system trustworthiness. Conventionally, trustworthy AI literature relies on the probabilistic framework…

机器学习 · 统计学 2024-01-05 Ritwik Vashistha , Arya Farahi

Current architectures to validate, certify, and manage identity are based on centralised, top-down approaches that rely on trusted authorities and third-party operators. We approach the problem of digital identity starting from a human…

计算机与社会 · 计算机科学 2020-02-26 Geoff Goodell , Tomaso Aste

In previous work ("Knowledge from Probability", TARK 2021) we develop a question-relative, probabilistic account of belief. On this account, what someone believes relative to a given question is (i) closed under entailment, (ii)…

人工智能 · 计算机科学 2023-07-13 Jeremy Goodman , Bernhard Salow

Artificial Intelligence (AI) has made impressive progress in recent years and represents a key technology that has a crucial impact on the economy and society. However, it is clear that AI and business models based on it can only reach…

Electronic identification (eID) systems allow citizens to assert and authenticate their identities for various purposes, such as accessing government services or conducting financial transactions. These systems improve user access to…

密码学与安全 · 计算机科学 2023-10-25 Jide Edu , Mark Hooper , Carsten Maple , Jon Crowcroft

An assurance case should provide justifiable confidence in the truth of a claim about some critical property of a system or procedure, such as safety or security. We consider how confidence can be assessed in the rigorous approach we call…

软件工程 · 计算机科学 2025-08-11 Robin Bloomfield , John Rushby

The need for AI systems to provide explanations for their behaviour is now widely recognised as key to their adoption. In this paper, we examine the problem of trustworthy AI and explore what delivering this means in practice, with a focus…

人工智能 · 计算机科学 2022-11-30 Rob Procter , Peter Tolmie , Mark Rouncefield

Correctness is an emergent property of systems where exposing error is cheaper than committing it. In dynamic, low-trust environments, autonomous AI agents benefit from delegating work to sub-agents, yet correctness cannot be assured…

计算机科学与博弈论 · 计算机科学 2025-12-03 David Shi , Kevin Joo

The promise of AI is huge. AI systems have already achieved good enough performance to be in our streets and in our homes. However, they can be brittle and unfair. For society to reap the benefits of AI systems, society needs to be able to…

人工智能 · 计算机科学 2020-02-18 Jeannette M. Wing

Autonomous systems with cognitive features are on their way into the market. Within complex environments, they promise to implement complex and goal oriented behavior even in a safety related context. This behavior is based on a certain…

人工智能 · 计算机科学 2020-02-20 Henrik J. Putzer , Ernest Wozniak

This thesis addresses the problem of providing trusted individuals with confidential information about other individuals, in particular, granting access to databases of personal records using the World-Wide Web. It proposes an access rights…

密码学与安全 · 计算机科学 2007-05-23 Walter Eaves
‹ 上一页 1 2 3 10 下一页 ›