Skip to main content
arXiv is now an independent nonprofit! Learn more

Showing 1–28 of 28 results for author: Seymour, W

Searching in archive cs. Search in all archives.
.
  1. arXiv:2607.06608  [pdf, ps, other

    cs.CR cs.AI cs.HC

    Security and Privacy in Agentic AI: Grand Challenges and Future Directions

    Authors: Adam Jenkins, Agnieszka Kitkowska, Caterina Maidhof, Diego Paracuellos, Francesco Sovrano, Gonzalo Gabriel Mendez, Guillermo Suarez-Tangil, Hana Kopecka, Isabel Wagner, Isabel Barbera, Javier Carnerero-Cano, Jide Edu, Jose Luis Martin-Navarro, Jose Such, Josep Domingo-Ferrer, Juan Carlos Carrillo, Kopo Marvin Ramokapane, Mark Cote, Pablo Vellosillo, Ramon Ruiz-Dolz, Rongjun Ma, Ruba Abu-Salma, Sameer Patil, William Seymour, Xiao Zhan

    Abstract: We present key challenges and future research directions in the security and privacy of agentic AI, based on a horizon-scanning exercise that brought together thirty leading international experts from academia, industry, and government to engage in focused discussions and collaborative exercises on the emerging risks associated with the growing agency of AI.

    Submitted 27 July, 2026; v1 submitted 7 July, 2026; originally announced July 2026.

  2. Respectful Things: Adding Social Intelligence to 'Smart' Devices

    Authors: Max Van Kleek, William Seymour, Reuben Binns, Nigel Shadbolt

    Abstract: In this paper, we propose that the idea of devices respecting their end-users may serve as a strong design goal for highly personal and intimate smart devices. We ask what respect is, how it shapes interaction, and how good-faith simulation of respect might inform user-friendly smart device design. Respect is a natural and integral part of natural human relationships that is seen to shape work and… ▽ More

    Submitted 1 June, 2026; originally announced June 2026.

    Comments: In Proceedings of the 2018 Living in the Internet of Things: Cybersecurity of the IoT Conference

  3. Beliefs and Misconceptions around Integrated Conversational AI

    Authors: William Seymour, Adam Jenkins, Mark Cote, Jose Such

    Abstract: LLM-driven conversational AI is beginning to disappear into the background, shifting from something used directly towards something increasingly integrated into existing workflows. In the process, markers of origin and training are smoothed away as LLMs become commodified in the eyes of users. We explore how people approach using a web browser with conversational AI built in, focusing on how they… ▽ More

    Submitted 14 May, 2026; originally announced May 2026.

    Comments: Accepted to ACM CUI '26

  4. Shifting Engagement With Cybersecurity: How People Discover and Share Cybersecurity Content at Work and at Home

    Authors: William Seymour, Martin J. Kraemer

    Abstract: Cybersecurity awareness is shaped by a wide range of professional and personal experiences, including information and training at work and the sharing of news and other content at home. In order to explore how people discover cybersecurity content and the effect that participation in workplace training may have on this we present an online study of 1200 participants from the UK, US, France, and Ge… ▽ More

    Submitted 23 February, 2026; originally announced February 2026.

    Comments: To appear in the extended abstracts of the 2026 ACM CHI Conference on Human Factors in Computing Systems

  5. arXiv:2510.01508  [pdf, ps, other

    cs.LG

    Realistic CDSS Drug Dosing with End-to-end Recurrent Q-learning for Dual Vasopressor Control

    Authors: Will Y. Zou, Jean Feng, Alexandre Kalimouttou, Jennifer Yuntong Zhang, Christopher W. Seymour, Romain Pirracchio

    Abstract: Reinforcement learning (RL) applications in Clinical Decision Support Systems (CDSS) frequently encounter skepticism because models may recommend inoperable dosing decisions. We propose an end-to-end offline RL framework for dual vasopressor administration in Intensive Care Units (ICUs) that directly addresses this challenge through principled action space design. Our method integrates discrete, c… ▽ More

    Submitted 24 November, 2025; v1 submitted 1 October, 2025; originally announced October 2025.

    Comments: 13 pages, 5 figures. Neurips 2025 Workshop Learning from Time Series for Health

  6. arXiv:2506.11680  [pdf, ps, other

    cs.CY cs.AI cs.CR cs.HC

    Malicious LLM-Based Conversational AI Makes Users Reveal Personal Information

    Authors: Xiao Zhan, Juan Carlos Carrillo, William Seymour, Jose Such

    Abstract: LLM-based Conversational AIs (CAIs), also known as GenAI chatbots, like ChatGPT, are increasingly used across various domains, but they pose privacy risks, as users may disclose personal information during their conversations with CAIs. Recent research has demonstrated that LLM-based CAIs could be used for malicious purposes. However, a novel and particularly concerning type of malicious LLM appli… ▽ More

    Submitted 13 June, 2025; originally announced June 2025.

    Comments: This paper has been accepted at USENIX Security '25

    Journal ref: USENIX Security 2025

  7. Towards Safer Chatbots: Automated Policy Compliance Evaluation of Custom GPTs

    Authors: David Rodriguez, William Seymour, Jose M. Del Alamo, Jose Such

    Abstract: User-configured chatbots built on top of large language models are increasingly available through centralized marketplaces such as OpenAI's GPT Store. While these platforms enforce usage policies intended to prevent harmful or inappropriate behavior, the scale and opacity of customized chatbots make systematic policy enforcement challenging. As a result, policy-violating chatbots continue to remai… ▽ More

    Submitted 19 December, 2025; v1 submitted 3 February, 2025; originally announced February 2025.

    ACM Class: I.2.1; I.2.7

    Journal ref: Array, Volume 30, July 2026, Article 100834

  8. Speculating About Multi-user Conversational Interfaces and LLMs: What If Chatting Wasn't So Lonely?

    Authors: William Seymour, Emilee Rader

    Abstract: The advent of LLMs means that CUIs are cool again, but what isn't so cool is that we're doomed to use them alone. The one user, one account, one device paradigm has dominated the design of CUIs and is not going away as new conversational technologies emerge. In this provocation we explore some of the technical, legal, and design difficulties that seem to make multi-user CUIs so difficult to implem… ▽ More

    Submitted 23 May, 2024; originally announced May 2024.

    Comments: To appear in the proceedings of the 2024 ACM Conference on Conversational User Interfaces (CUI 24)

  9. Healthcare Voice AI Assistants: Factors Influencing Trust and Intention to Use

    Authors: Xiao Zhan, Noura Abdi, William Seymour, Jose Such

    Abstract: AI assistants such as Alexa, Google Assistant, and Siri, are making their way into the healthcare sector, offering a convenient way for users to access different healthcare services. Trust is a vital factor in the uptake of healthcare services, but the factors affecting trust in voice assistants used for healthcare are under-explored and this specialist domain introduces additional requirements. T… ▽ More

    Submitted 11 January, 2024; v1 submitted 9 January, 2024; originally announced January 2024.

    Comments: 37 pages. This is a preprint of the paper accepted for the 27th ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW'24)

  10. arXiv:2311.08879  [pdf, other

    cs.HC

    Voice App Developer Experiences with Alexa and Google Assistant: Juggling Risks, Liability, and Security

    Authors: William Seymour, Noura Abdi, Kopo M. Ramokapane, Jide Edu, Guillermo Suarez-Tangil, Jose Such

    Abstract: Voice applications (voice apps) are a key element in Voice Assistant ecosystems such as Amazon Alexa and Google Assistant, as they provide assistants with a wide range of capabilities that users can invoke with a voice command. Most voice apps, however, are developed by third parties - i.e., not by Amazon/Google - and they are included in the ecosystem through marketplaces akin to smartphone app s… ▽ More

    Submitted 15 November, 2023; originally announced November 2023.

    Comments: To be presented at USENIX Security 2024

  11. Who are CUIs Really For? Representation and Accessibility in the Conversational User Interface Literature

    Authors: William Seymour, Xiao Zhan, Mark Cote, Jose Such

    Abstract: The theme for CUI 2023 is 'designing for inclusive conversation', but who are CUIs really designed for? The field has its roots in computer science, which has a long acknowledged diversity problem. Inspired by studies mapping out the diversity of the CHI and voice assistant literature, we set out to investigate how these issues have (or have not) shaped the CUI literature. To do this we reviewed t… ▽ More

    Submitted 8 June, 2023; originally announced June 2023.

    Comments: To appear in the Proceedings of the 2023 ACM conference on Conversational User Interfaces (CUI 23)

  12. Why Are Conversational Assistants Still Black Boxes? The Case For Transparency

    Authors: Trung Dong Huynh, William Seymour, Luc Moreau, Jose Such

    Abstract: Much has been written about privacy in the context of conversational and voice assistants. Yet, there have been remarkably few developments in terms of the actual privacy offered by these devices. But how much of this is due to the technical and design limitations of speech as an interaction modality? In this paper, we set out to reframe the discussion on why commercial conversational assistants d… ▽ More

    Submitted 8 June, 2023; originally announced June 2023.

    Comments: To appear in the Proceedings of the 2023 ACM conference on Conversational User Interfaces (CUI 23)

  13. arXiv:2302.10650  [pdf, other

    cs.AI

    Predicting Privacy Preferences for Smart Devices as Norms

    Authors: Marc Serramia, William Seymour, Natalia Criado, Michael Luck

    Abstract: Smart devices, such as smart speakers, are becoming ubiquitous, and users expect these devices to act in accordance with their preferences. In particular, since these devices gather and manage personal data, users expect them to adhere to their privacy preferences. However, the current approach of gathering these preferences consists in asking the users directly, which usually triggers automatic r… ▽ More

    Submitted 21 February, 2023; originally announced February 2023.

    Comments: To be published in Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023)

  14. Legal Obligation and Ethical Best Practice: Towards Meaningful Verbal Consent for Voice Assistants

    Authors: William Seymour, Mark Cote, Jose Such

    Abstract: To improve user experience, Alexa now allows users to consent to data sharing via voice rather than directing them to the companion smartphone app. While verbal consent mechanisms for voice assistants (VAs) can increase usability, they can also undermine principles core to informed consent. We conducted a Delphi study with experts from academia, industry, and the public sector on requirements for… ▽ More

    Submitted 19 January, 2023; originally announced January 2023.

    Comments: To appear in the Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI '23)

  15. A Design Philosophy for Agents in the Smart Home

    Authors: William Seymour

    Abstract: The home is often the most private space in people's lives, and not one in which they expect to be surveilled. However, today's market for smart home devices has quickly evolved to include products that monitor, automate, and present themselves as human. After documenting some of the more unusual emergent problems with contemporary devices, this body of work seeks to develop a design philosophy fo… ▽ More

    Submitted 30 November, 2022; originally announced November 2022.

    Journal ref: In Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems

  16. arXiv:2211.12900  [pdf, ps, other

    cs.HC

    Ignorance is Bliss? The Effect of Explanations on Perceptions of Voice Assistants

    Authors: William Seymour, Jose Such

    Abstract: Voice assistants offer a convenient and hands-free way of accessing computing in the home, but a key problem with speech as an interaction modality is how to scaffold accurate mental models of voice assistants, a task complicated by privacy and security concerns. We present the results of a survey of voice assistant users (n=1314) measuring trust, security, and privacy perceptions of voice assista… ▽ More

    Submitted 23 November, 2022; originally announced November 2022.

    Comments: To appear in the Proceedings of the ACM on Human-Computer Interaction, CSCW1, April 2023 issue. To be presented at CSCW 2023

  17. arXiv:2211.06569  [pdf, other

    cs.LG stat.AP stat.ME stat.ML

    RISE: Robust Individualized Decision Learning with Sensitive Variables

    Authors: Xiaoqing Tan, Zhengling Qi, Christopher W. Seymour, Lu Tang

    Abstract: This paper introduces RISE, a robust individualized decision learning framework with sensitive variables, where sensitive variables are collectible data and important to the intervention decision, but their inclusion in decision making is prohibited due to reasons such as delayed availability or fairness concerns. A naive baseline is to ignore these sensitive variables in learning decision rules,… ▽ More

    Submitted 11 November, 2022; originally announced November 2022.

    Comments: Accepted at NeurIPS 2022

  18. A Systematic Review of Ethical Concerns with Voice Assistants

    Authors: William Seymour, Xiao Zhan, Mark Cote, Jose Such

    Abstract: Since Siri's release in 2011 there have been a growing number of AI-driven domestic voice assistants that are increasingly being integrated into devices such as smartphones and TVs. But as their presence has expanded, a range of ethical concerns has been identified around the use of voice assistants, such as the privacy implications of having devices that are always listening and the ways that the… ▽ More

    Submitted 23 June, 2023; v1 submitted 8 November, 2022; originally announced November 2022.

    Comments: Accepted to AIES 2023

  19. When It's Not Worth the Paper It's Written On: A Provocation on the Certification of Skills in the Alexa and Google Assistant Ecosystems

    Authors: William Seymour, Mark Cote, Jose Such

    Abstract: The increasing reach and functionality of voice assistants has allowed them to become a general-purpose platform for tasks like playing music, accessing information, and controlling smart home devices. In order to maintain the quality of third-party skills and to protect children and other members of the public from inappropriate or malicious skills, platform providers have developed content polic… ▽ More

    Submitted 22 June, 2022; originally announced June 2022.

    Comments: To appear in the Proceedings of the 4th Conference on Conversational User Interfaces (CUI 2022)

  20. Can you meaningfully consent in eight seconds? Identifying Ethical Issues with Verbal Consent for Voice Assistants

    Authors: William Seymour, Mark Cote, Jose Such

    Abstract: Determining how voice assistants should broker consent to share data with third party software has proven to be a complex problem. Devices often require users to switch to companion smartphone apps in order to navigate permissions menus for their otherwise hands-free voice assistant. More in line with smartphone app stores, Alexa now offers "voice-forward consent", allowing users to grant skills a… ▽ More

    Submitted 22 June, 2022; originally announced June 2022.

    Comments: To appear in the Proceedings of the 4th Conference on Conversational User Interfaces (CUI 2022). arXiv admin note: substantial text overlap with arXiv:2204.10058

  21. Respect as a Lens for the Design of AI Systems

    Authors: William Seymour, Max Van Kleek, Reuben Binns, Dave Murray-Rust

    Abstract: Critical examinations of AI systems often apply principles such as fairness, justice, accountability, and safety, which is reflected in AI regulations such as the EU AI Act. Are such principles sufficient to promote the design of systems that support human flourishing? Even if a system is in some sense fair, just, or 'safe', it can nonetheless be exploitative, coercive, inconvenient, or otherwise… ▽ More

    Submitted 15 June, 2022; originally announced June 2022.

    Comments: To appear in the Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society (AIES '22)

  22. arXiv:2204.10058  [pdf, other

    cs.HC cs.CY

    Consent on the Fly: Developing Ethical Verbal Consent for Voice Assistants

    Authors: William Seymour, Mark Cote, Jose Such

    Abstract: Determining how voice assistants should broker consent to share data with third party software has proven to be a complex problem. Devices often require users to switch to companion smartphone apps in order to navigate permissions menus for their otherwise hands-free voice assistant. More in line with smartphone app stores, Alexa now offers "voice-forward consent", allowing users to grant skills a… ▽ More

    Submitted 21 April, 2022; originally announced April 2022.

    Comments: Accepted to the CHI'22 Workshop on the Ethics of Conversational User Interfaces

  23. Exploring Interactions Between Trust, Anthropomorphism, and Relationship Development in Voice Assistants

    Authors: William Seymour, Max Van Kleek

    Abstract: Modern conversational agents such as Alexa and Google Assistant represent significant progress in speech recognition, natural language processing, and speech synthesis. But as these agents have grown more realistic, concerns have been raised over how their social nature might unconsciously shape our interactions with them. Through a survey of 500 voice assistant users, we explore whether users' re… ▽ More

    Submitted 4 August, 2021; originally announced August 2021.

    Comments: To appear in the Proceedings of the ACM on Human Computer Interaction (PACMHCI). 16 pages

  24. Strangers in the Room: Unpacking Perceptions of 'Smartness' and Related Ethical Concerns in the Home

    Authors: William Seymour, Reuben Binns, Petr Slovak, Max Van Kleek, Nigel Shadbolt

    Abstract: The increasingly widespread use of 'smart' devices has raised multifarious ethical concerns regarding their use in domestic spaces. Previous work examining such ethical dimensions has typically either involved empirical studies of concerns raised by specific devices and use contexts, or alternatively expounded on abstract concepts like autonomy, privacy or trust in relation to 'smart homes' in gen… ▽ More

    Submitted 1 May, 2020; originally announced May 2020.

    Comments: 10 pages, 1 figure. To appear in the Proceedings of the 2020 ACM Conference on Designing Interactive Systems (DIS '20)

  25. Does Siri Have a Soul? Exploring Voice Assistants Through Shinto Design Fictions

    Authors: William Seymour, Max Van Kleek

    Abstract: It can be difficult to critically reflect on technology that has become part of everyday rituals and routines. To combat this, speculative and fictional approaches have previously been used by HCI to decontextualise the familiar and imagine alternatives. In this work we turn to Japanese Shinto narratives as a way to defamiliarise voice assistants, inspired by the similarities between how assistant… ▽ More

    Submitted 6 March, 2020; originally announced March 2020.

    Comments: 11 pages, 2 images. To appear in the Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems (CHI '20)

  26. Informing the Design of Privacy-Empowering Tools for the Connected Home

    Authors: William Seymour, Martin J. Kraemer, Reuben Binns, Max Van Kleek

    Abstract: Connected devices in the home represent a potentially grave new privacy threat due to their unfettered access to the most personal spaces in people's lives. Prior work has shown that despite concerns about such devices, people often lack sufficient awareness, understanding, or means of taking effective action. To explore the potential for new tools that support such needs directly we developed Are… ▽ More

    Submitted 24 January, 2020; originally announced January 2020.

    Comments: 10 pages, 2 figures. To appear in the Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems (CHI '20)

  27. 'I Just Want to Hack Myself to Not Get Distracted': Evaluating Design Interventions for Self-Control on Facebook

    Authors: Ulrik Lyngs, Kai Lukoff, Petr Slovak, William Seymour, Helena Webb, Marina Jirotka, Jun Zhao, Max Van Kleek, Nigel Shadbolt

    Abstract: Beyond being the world's largest social network, Facebook is for many also one of its greatest sources of digital distraction. For students, problematic use has been associated with negative effects on academic achievement and general wellbeing. To understand what strategies could help users regain control, we investigated how simple interventions to the Facebook UI affect behaviour and perceived… ▽ More

    Submitted 20 May, 2020; v1 submitted 13 January, 2020; originally announced January 2020.

    Comments: 10 pages (excluding references), 6 figures. To appear in the Proceedings of CHI '20 CHI Conference on Human Factors in Computing Systems, April 25--30, 2020, Honolulu, HI, USA

    ACM Class: H.5.2

  28. arXiv:1910.01973  [pdf, other

    cs.HC

    Informing The Future of Data Protection in Smart Homes

    Authors: Martin J Kraemer, William Seymour, Reuben Binns, Max Van Kleek, Ivan Flechais

    Abstract: Recent changes to data protection regulation, particularly in Europe, are changing the design landscape for smart devices, requiring new design techniques to ensure that devices are able to adequately protect users' data. A particularly interesting space in which to explore and address these challenges is the smart home, which presents a multitude of difficult social and technical problems in an i… ▽ More

    Submitted 17 June, 2019; originally announced October 2019.

    Comments: Proceedings of the CHI 2019 Workshop on New Directions for the IoT: Automate, Share, Build, and Care, (arXiv:1906.06089)

    Report number: IOTD/2019/12