XAI to Explore Robustness of Features in Adversarial Training for Cybersecurity

AL-Essa, Malik; Andresini, Giuseppina; Appice, Annalisa; Malerba, Donato

doi:10.1007/978-3-031-16564-1_12

Cited by 4 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Otherwise, A high level of explainability and interpretability could assist in improving model performance and robustness [61]. This study verified the effectiveness of data bias removal and model enhancement processes in enhancing the robustness of AMD detection by evaluating accuracy results for unseen test datasets.…”

Section: Discussionsupporting

confidence: 57%

An Explainable Artificial Intelligence-Based Robustness Optimization Approach for Age-Related Macular Degeneration Detection Based on Medical IOT Systems

et al. 2023

View full text Add to dashboard Cite

AI-based models have shown promising results in diagnosing eye diseases based on multi-sources of data collected from medical IOT systems. However, there are concerns regarding their generalization and robustness, as these methods are prone to overfitting specific datasets. The development of Explainable Artificial Intelligence (XAI) techniques has addressed the black-box problem of machine learning and deep learning models, which can enhance interpretability and trustworthiness and optimize their performance in the real world. Age-related macular degeneration (AMD) is currently the primary cause of vision loss among elderly individuals. In this study, XAI methods were applied to detect AMD using various ophthalmic imaging modalities collected from medical IOT systems, such as colorful fundus photography (CFP), optical coherence tomography (OCT), ultra-wide fundus (UWF) images, and fluorescein angiography fundus (FAF). An optimized deep learning (DL) model and novel AMD identification systems were proposed based on the insights extracted by XAI. The findings of this study demonstrate that XAI not only has the potential to improve the transparency, reliability, and trustworthiness of AI models for ophthalmic applications, but it also has significant advantages for enhancing the robustness performance of these models. XAI could play a crucial role in promoting intelligent ophthalmology and be one of the most important techniques for evaluating and enhancing ophthalmic AI systems.

show abstract

Section: Discussionsupporting

confidence: 57%

An Explainable Artificial Intelligence-Based Robustness Optimization Approach for Age-Related Macular Degeneration Detection Based on Medical IOT Systems

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Nadeem et al [25] focus on the use of XAI for both defensive and offensive cybersecurity tasks, identifying three key stakeholders-model users, designers, and adversaries-and outlining four primary objectives for integrating XAI within the machine learning pipeline. Al-Azzawi et al [26] explore the accuracy of adversarial training in cybersecurity, utilizing XAI to analyze the impact of input features on model decisions and to facilitate robust feature selection. Kuppa et al [27] examine the potential risks associated with XAI methods in cybersecurity, particularly how model explanations might introduce new attack surfaces.…”

Section: Xai In Cybersecuritymentioning

confidence: 99%

Interpretability and Transparency of Machine Learning in File Fragment Analysis with Explainable Artificial Intelligence

Jinad,

Islam,

Shashidhar

2024

Electronics

View full text Add to dashboard Cite

Machine learning models are increasingly being used across diverse fields, including file fragment classification. As these models become more prevalent, it is crucial to understand and interpret their decision-making processes to ensure accountability, transparency, and trust. This research investigates the interpretability of four machine learning models used for file fragment classification through the lens of Explainable Artificial Intelligence (XAI) techniques. Specifically, we employ two prominent XAI methods, Shapley Additive Explanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME), to shed light on the black-box nature of four machine learning models used for file fragment classification. By conducting a detailed analysis of the SHAP and LIME explanations, we demonstrate the effectiveness of these techniques in improving the interpretability of the models’ decision-making processes. Our analysis reveals that these XAI techniques effectively identify key features influencing each model’s predictions. The results also showed features that were critical to predicting specific classes. The ability to interpret and validate the decisions made by machine learning models in file fragment classification can enhance trust in these models and inform improvements for better accuracy and reliability. Our research highlights the importance of XAI techniques in promoting transparency and accountability in the application of machine learning models across diverse domains.

show abstract