4 papers
Beyond Gradient-Based Attacks: Adversarial Robustness and Explainability Stability in Cybersecurity Classifiers
Mona Rajhans, Vishal Khawarey
Adversarial attacks on cybersecurity classifiers pose a dual threat: degrading predictions and destabilising the SHAP-based explanations that security analysts rely on to understan…
Automated Multi-Source Debugging and Natural Language Error Explanation for Dashboard Applications
Devendra Tata, Mona Rajhans
Modern web dashboards and enterprise applications increasingly rely on complex, distributed microservices architectures. While these architectures offer scalability, they introduce…
An Information-Theoretic Framework for Comparing Voice and Text Explainability
Mona Rajhans, Vishal Khawarey
Explainable Artificial Intelligence (XAI) aims to make machine learning models transparent and trustworthy, yet most current approaches communicate explanations visually or through…
Empirical Analysis of Adversarial Robustness and Explainability Drift in Cybersecurity Classifiers
Mona Rajhans, Vishal Khawarey
Machine learning (ML) models are increasingly deployed in cybersecurity applications such as phishing detection and network intrusion prevention. However, these models remain vulne…