Rethinking Explainable AI: Explanations can be Deceiving

Peta Masters; Daniel Gallagher; Luc Moreau; Mor Vered

Rethinking Explainable AI: Explanations can be Deceiving

Peta Masters
, Daniel Gallagher
, Luc Moreau
, Mor Vered

King's College London
Monash University
University of Sussex

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

The propensity to overtrust explanations and over-rely on systems that seem transparent makes humans vulnerable to output that conforms to explainable AI (XAI) best practice. Human-centred XAI research seeks to determine the type of explanation most appropriate in any particular context. Other disciplines, meanwhile, provide insights into the way deception has tended to arise in relation to AI systems. Examining XAI research in this context, we find it a perfect melting pot for the generation of deceptive explanations. We demonstrate the problem in a user study and provide and evaluate recommendations for stakeholders.

Original language	English
Title of host publication	Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025
Editors	Yevgeniy Vorobeychik, Sanmay Das, Ann Nowe
Publisher	International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Pages	2663-2665
Number of pages	3
ISBN (Electronic)	9798400714269
State	Published - 2025
Externally published	Yes
Event	24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025 - Detroit, United States Duration: 19 May 2025 → 23 May 2025

Publication series

Name	Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
ISSN (Print)	1548-8403
ISSN (Electronic)	1558-2914

Conference

Conference	24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025
Country/Territory	United States
City	Detroit
Period	19/05/25 → 23/05/25

Bibliographical note

Publisher Copyright:
© 2025 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org).

Keywords

Deception
Explainability
Recommendations
eXplainable AI

Cite this

Masters, P., Gallagher, D., Moreau, L., & Vered, M. (2025). Rethinking Explainable AI: Explanations can be Deceiving. In Y. Vorobeychik, S. Das, & A. Nowe (Eds.), Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025 (pp. 2663-2665). (Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS). International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).

Masters, Peta ; Gallagher, Daniel ; Moreau, Luc et al. / Rethinking Explainable AI : Explanations can be Deceiving. Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025. editor / Yevgeniy Vorobeychik ; Sanmay Das ; Ann Nowe. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2025. pp. 2663-2665 (Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS).

@inproceedings{4ebdaea310d240669cf468e6bd63d7e2,

title = "Rethinking Explainable AI: Explanations can be Deceiving",

abstract = "The propensity to overtrust explanations and over-rely on systems that seem transparent makes humans vulnerable to output that conforms to explainable AI (XAI) best practice. Human-centred XAI research seeks to determine the type of explanation most appropriate in any particular context. Other disciplines, meanwhile, provide insights into the way deception has tended to arise in relation to AI systems. Examining XAI research in this context, we find it a perfect melting pot for the generation of deceptive explanations. We demonstrate the problem in a user study and provide and evaluate recommendations for stakeholders.",

keywords = "Deception, Explainability, Recommendations, eXplainable AI",

author = "Peta Masters and Daniel Gallagher and Luc Moreau and Mor Vered",

note = "Publisher Copyright: {\textcopyright} 2025 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org).; 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025 ; Conference date: 19-05-2025 Through 23-05-2025",

year = "2025",

language = "אנגלית",

series = "Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS",

publisher = "International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)",

pages = "2663--2665",

editor = "Yevgeniy Vorobeychik and Sanmay Das and Ann Nowe",

booktitle = "Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025",

}

Masters, P, Gallagher, D, Moreau, L & Vered, M 2025, Rethinking Explainable AI: Explanations can be Deceiving. in Y Vorobeychik, S Das & A Nowe (eds), Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025. Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), pp. 2663-2665, 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025, Detroit, United States, 19/05/25.

Rethinking Explainable AI: Explanations can be Deceiving. / Masters, Peta; Gallagher, Daniel; Moreau, Luc et al.
Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025. ed. / Yevgeniy Vorobeychik; Sanmay Das; Ann Nowe. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2025. p. 2663-2665 (Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Rethinking Explainable AI

T2 - 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025

AU - Masters, Peta

AU - Gallagher, Daniel

AU - Moreau, Luc

AU - Vered, Mor

PY - 2025

Y1 - 2025

N2 - The propensity to overtrust explanations and over-rely on systems that seem transparent makes humans vulnerable to output that conforms to explainable AI (XAI) best practice. Human-centred XAI research seeks to determine the type of explanation most appropriate in any particular context. Other disciplines, meanwhile, provide insights into the way deception has tended to arise in relation to AI systems. Examining XAI research in this context, we find it a perfect melting pot for the generation of deceptive explanations. We demonstrate the problem in a user study and provide and evaluate recommendations for stakeholders.

AB - The propensity to overtrust explanations and over-rely on systems that seem transparent makes humans vulnerable to output that conforms to explainable AI (XAI) best practice. Human-centred XAI research seeks to determine the type of explanation most appropriate in any particular context. Other disciplines, meanwhile, provide insights into the way deception has tended to arise in relation to AI systems. Examining XAI research in this context, we find it a perfect melting pot for the generation of deceptive explanations. We demonstrate the problem in a user study and provide and evaluate recommendations for stakeholders.

KW - Deception

KW - Explainability

KW - Recommendations

KW - eXplainable AI

UR - https://www.scopus.com/pages/publications/105009843118

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:105009843118

T3 - Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS

SP - 2663

EP - 2665

BT - Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025

A2 - Vorobeychik, Yevgeniy

A2 - Das, Sanmay

A2 - Nowe, Ann

PB - International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)

Y2 - 19 May 2025 through 23 May 2025

ER -

Masters P, Gallagher D, Moreau L, Vered M. Rethinking Explainable AI: Explanations can be Deceiving. In Vorobeychik Y, Das S, Nowe A, editors, Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS). 2025. p. 2663-2665. (Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS).

Rethinking Explainable AI: Explanations can be Deceiving

Abstract

Publication series

Conference

Bibliographical note

Keywords

Other files and links

Fingerprint

Cite this