Using XAI Techniques to Detect Targeted Data Poisoning Attacks on Healthcare Applications of Machine Learning Systems

This research study explores the application of Explainable Artificial Intelligence (XAI) methods for detecting targeted data poisoning attacks in healthcare machine learning systems. As machine learning becomes increasingly integrated into critical fields like healthcare, the integrity and security...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Eyad Dhaher Megdadi (author)
مؤلفون آخرون: Usman Javed Butt (author)
منشور في: 2025
الوصول للمادة أونلاين:https://bspace.buid.ac.ae/handle/1234/3130
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1862980613914492928
author Eyad Dhaher Megdadi
author2 Usman Javed Butt
author2_role author
author_facet Eyad Dhaher Megdadi
Usman Javed Butt
author_role author
dc.creator.none.fl_str_mv Eyad Dhaher Megdadi
Usman Javed Butt
dc.date.none.fl_str_mv 2025-05-27T11:57:34Z
2025-05-27T11:57:34Z
2025
dc.identifier.none.fl_str_mv Megdadi, E.D., Butt, U.J. (2025). Using XAI Techniques to Detect Targeted Data Poisoning Attacks on Healthcare Applications of Machine Learning Systems. In: Al Marri, K., Mir, F.A., Awad, A., Abubakar, A. (eds) BUiD Doctoral Research Conference 2024. BDRC 2024. Lecture Notes in Civil Engineering, vol 587. Springer, Cham. https://doi.org/10.1007/978-3-031-84371-6_40
HB: 9783031843709 eBook: 9783031843716
https://bspace.buid.ac.ae/handle/1234/3130
dc.language.none.fl_str_mv en
dc.publisher.none.fl_str_mv Springer Cham
dc.relation.none.fl_str_mv Lecture Notes in Civil Engineering; 587
dc.title.none.fl_str_mv Using XAI Techniques to Detect Targeted Data Poisoning Attacks on Healthcare Applications of Machine Learning Systems
dc.type.none.fl_str_mv Book chapter
description This research study explores the application of Explainable Artificial Intelligence (XAI) methods for detecting targeted data poisoning attacks in healthcare machine learning systems. As machine learning becomes increasingly integrated into critical fields like healthcare, the integrity and security of training data have become paramount concerns. Data poisoning attacks, which manipulate training datasets to influence model behaviour, pose a significant threat to the reliability and effectiveness of these systems. Our study presents a novel approach that leverages XAI techniques, particularly focusing on global explanations of selected features, to identify signs of data manipulation. We propose a method of monitoring the impact level of carefully chosen features as an indicator of potential poisoning, using predetermined thresholds to trigger warnings when unusual patterns are detected. The research methodology involves applying global explanation method, to measure and monitor features impact in healthcare datasets, then explore the effectiveness of this approach using a case study on hypothyroid diagnosis, where data poisoning could lead to delayed treatment with potentially life-threatening consequences. Research findings suggest that XAI techniques can provide valuable insights into the behaviour of machine learning models, enabling more effective detection of subtle, targeted poisoning attacks. However, we also acknowledge limitations, including the need for some prior knowledge of potential attack goals and the risk of false positives or negatives.
id budr_e857c919fad65619084796650c9d06d5
identifier_str_mv Megdadi, E.D., Butt, U.J. (2025). Using XAI Techniques to Detect Targeted Data Poisoning Attacks on Healthcare Applications of Machine Learning Systems. In: Al Marri, K., Mir, F.A., Awad, A., Abubakar, A. (eds) BUiD Doctoral Research Conference 2024. BDRC 2024. Lecture Notes in Civil Engineering, vol 587. Springer, Cham. https://doi.org/10.1007/978-3-031-84371-6_40
HB: 9783031843709 eBook: 9783031843716
language_invalid_str_mv en
network_acronym_str budr
network_name_str The British University in Dubai repository
oai_identifier_str oai:bspace.buid.ac.ae:1234/3130
publishDate 2025
publisher.none.fl_str_mv Springer Cham
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Using XAI Techniques to Detect Targeted Data Poisoning Attacks on Healthcare Applications of Machine Learning SystemsEyad Dhaher MegdadiUsman Javed ButtThis research study explores the application of Explainable Artificial Intelligence (XAI) methods for detecting targeted data poisoning attacks in healthcare machine learning systems. As machine learning becomes increasingly integrated into critical fields like healthcare, the integrity and security of training data have become paramount concerns. Data poisoning attacks, which manipulate training datasets to influence model behaviour, pose a significant threat to the reliability and effectiveness of these systems. Our study presents a novel approach that leverages XAI techniques, particularly focusing on global explanations of selected features, to identify signs of data manipulation. We propose a method of monitoring the impact level of carefully chosen features as an indicator of potential poisoning, using predetermined thresholds to trigger warnings when unusual patterns are detected. The research methodology involves applying global explanation method, to measure and monitor features impact in healthcare datasets, then explore the effectiveness of this approach using a case study on hypothyroid diagnosis, where data poisoning could lead to delayed treatment with potentially life-threatening consequences. Research findings suggest that XAI techniques can provide valuable insights into the behaviour of machine learning models, enabling more effective detection of subtle, targeted poisoning attacks. However, we also acknowledge limitations, including the need for some prior knowledge of potential attack goals and the risk of false positives or negatives.Springer Cham2025-05-27T11:57:34Z2025-05-27T11:57:34Z2025Book chapterMegdadi, E.D., Butt, U.J. (2025). Using XAI Techniques to Detect Targeted Data Poisoning Attacks on Healthcare Applications of Machine Learning Systems. In: Al Marri, K., Mir, F.A., Awad, A., Abubakar, A. (eds) BUiD Doctoral Research Conference 2024. BDRC 2024. Lecture Notes in Civil Engineering, vol 587. Springer, Cham. https://doi.org/10.1007/978-3-031-84371-6_40HB: 9783031843709 eBook: 9783031843716https://bspace.buid.ac.ae/handle/1234/3130enLecture Notes in Civil Engineering; 587oai:bspace.buid.ac.ae:1234/31302025-05-27T11:57:35Z
spellingShingle Using XAI Techniques to Detect Targeted Data Poisoning Attacks on Healthcare Applications of Machine Learning Systems
Eyad Dhaher Megdadi
title Using XAI Techniques to Detect Targeted Data Poisoning Attacks on Healthcare Applications of Machine Learning Systems
title_full Using XAI Techniques to Detect Targeted Data Poisoning Attacks on Healthcare Applications of Machine Learning Systems
title_fullStr Using XAI Techniques to Detect Targeted Data Poisoning Attacks on Healthcare Applications of Machine Learning Systems
title_full_unstemmed Using XAI Techniques to Detect Targeted Data Poisoning Attacks on Healthcare Applications of Machine Learning Systems
title_short Using XAI Techniques to Detect Targeted Data Poisoning Attacks on Healthcare Applications of Machine Learning Systems
title_sort Using XAI Techniques to Detect Targeted Data Poisoning Attacks on Healthcare Applications of Machine Learning Systems
url https://bspace.buid.ac.ae/handle/1234/3130