Cover Image

Stabilising Explainability Fragility in Cybersecurity AI: The Impact and Mitigation of Multicollinearity in Public Benchmark Datasets

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Vourganas, Ioannis J., Michala, Anna Lito
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Explainable Artificial Intelligence and Multicollinearity : A Mini Review of Current Approaches
by: Salih, Ahmed M
Published: (2024)

Detecting Cybersecurity Threats by Integrating Explainable AI with SHAP Interpretability and Strategic Data Sampling
by: Srisumrith, Norrakith, et al.
Published: (2026)

Tensor Networks for Explainable Machine Learning in Cybersecurity
by: Aizpurua, Borja, et al.
Published: (2023)

A Comprehensive Perspective on Explainable AI across the Machine Learning Workflow
by: Paterakis, George, et al.
Published: (2025)

BEExAI: Benchmark to Evaluate Explainable AI
by: Sithakoul, Samuel, et al.
Published: (2024)

Mind the XAI Gap: A Human-Centered LLM Framework for Democratizing Explainable AI
by: Paraschou, Eva, et al.
Published: (2025)

Exploring Nutritional Impact on Alzheimer's Mortality: An Explainable AI Approach
by: Liu, Ziming, et al.
Published: (2024)

On The Fragility of Benchmark Contamination Detection in Reasoning Models
by: Wang, Han, et al.
Published: (2025)

Empirical Analysis of Adversarial Robustness and Explainability Drift in Cybersecurity Classifiers
by: Rajhans, Mona, et al.
Published: (2026)

Explainability of Complex AI Models with Correlation Impact Ratio
by: Sengupta, Poushali, et al.
Published: (2026)

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
by: Korbak, Tomek, et al.
Published: (2025)

Graph Counterfactual Explainable AI via Latent Space Traversal
by: Hansen, Andreas Abildtrup, et al.
Published: (2025)

Assessing Trustworthiness of AI Training Dataset using Subjective Logic -- A Use Case on Bias
by: Ouattara, Koffi Ismael, et al.
Published: (2025)

Learning-to-Explain through 20Q Gaming: An Explainable Recommender for Cybersecurity Education
by: Nusrat, Mary, et al.
Published: (2026)

Explainable AI in Time-Sensitive Scenarios: Prefetched Offline Explanation Model
by: Russo, Fabio Michele, et al.
Published: (2025)

Autonomous AI-based Cybersecurity Framework for Critical Infrastructure: Real-Time Threat Mitigation
by: Paulraj, Jenifer, et al.
Published: (2025)

Three Concrete Challenges and Two Hopes for the Safety of Unsupervised Elicitation
by: Canavan, Callum, et al.
Published: (2026)

Explainable AI needs formalization
by: Haufe, Stefan, et al.
Published: (2024)

The ecosystem of machine learning competitions: Platforms, participants, and their impact on AI development
by: Nasios, Ioannis
Published: (2026)

Explainable fault and severity classification for rolling element bearings using Kolmogorov-Arnold networks
by: Rigas, Spyros, et al.
Published: (2024)

FLAME: Adaptive and Reactive Concept Drift Mitigation for Federated Learning Deployments
by: Mavromatis, Ioannis, et al.
Published: (2024)

Explainable AI for Classifying UTI Risk Groups Using a Real-World Linked EHR and Pathology Lab Dataset
by: Dai, Yujie, et al.
Published: (2024)

Rethinking Explainability in the Era of Multimodal AI
by: Agarwal, Chirag
Published: (2025)

Explainable AI For Early Detection Of Sepsis
by: Thakur, Atharva, et al.
Published: (2025)

Verifying Machine Unlearning with Explainable AI
by: Vidal, Àlex Pujol, et al.
Published: (2024)

XAI-Units: Benchmarking Explainability Methods with Unit Tests
by: Lee, Jun Rui, et al.
Published: (2025)

Concept-Based Explainable Artificial Intelligence: Metrics and Benchmarks
by: Aysel, Halil Ibrahim, et al.
Published: (2025)

Towards Mitigating Architecture Overfitting on Distilled Datasets
by: Zhong, Xuyang, et al.
Published: (2023)

Privacy Meets Explainability: A Comprehensive Impact Benchmark
by: Saifullah, Saifullah, et al.
Published: (2022)

A Backdoor-based Explainable AI Benchmark for High Fidelity Evaluation of Attributions
by: Yang, Peiyu, et al.
Published: (2024)

Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability
by: Ky, Joël Roman, et al.
Published: (2026)

Framing AI System Benchmarking as a Learning Task: FlexBench and the Open MLPerf Dataset
by: Fursin, Grigori, et al.
Published: (2025)

Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science
by: Bommer, Philine, et al.
Published: (2023)

On the Fragility of AI-Based Channel Decoders under Small Channel Perturbations
by: Lei, Haoyu, et al.
Published: (2026)

AI-Cybersecurity Education Through Designing AI-based Cyberharassment Detection Lab
by: Okpala, Ebuka, et al.
Published: (2024)

Analyzing the Impact of Adversarial Examples on Explainable Machine Learning
by: Devabhakthini, Prathyusha, et al.
Published: (2023)

ExECG: An Explainable AI Framework for ECG models
by: Jang, Jong-Hwan, et al.
Published: (2026)

Explainable AI for Fair Sepsis Mortality Predictive Model
by: Chang, Chia-Hsuan, et al.
Published: (2024)

Guided Game Level Repair via Explainable AI
by: Bazzaz, Mahsa, et al.
Published: (2024)

Neuro-Symbolic AI: Explainability, Challenges, and Future Trends
by: Zhang, Xin, et al.
Published: (2024)