10 papers
Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation
Ahsan Habib Akash, Dipkamal Bhusal, Stacey Jones +3
Deep neural networks are widely deployed in high-stakes visual applications where interpretability is critical, yet existing explanations face a trade-off: post-hoc concept methods…
H-Sets: Hessian-Guided Discovery of Set-Level Feature Interactions in Image Classifiers
Ayushi Mehrotra, Dipkamal Bhusal, Michael Clifford +1
Feature attribution methods explain the predictions of deep neural networks by assigning importance scores to individual input features. However, most existing methods focus solely…
Training for Trustworthy Saliency Maps: Adversarial Training Meets Feature-Map Smoothing
Dipkamal Bhusal, Md Tanvirul Alam, Nidhi Rastogi
Gradient-based saliency methods such as Vanilla Gradient (VG) and Integrated Gradients (IG) are widely used to explain image classifiers, yet the resulting maps are often noisy and…
AthenaBench: A Dynamic Benchmark for Evaluating LLMs in Cyber Threat Intelligence
Md Tanvirul Alam, Dipkamal Bhusal, Salman Ahmad +2
Large Language Models (LLMs) have demonstrated strong capabilities in natural language reasoning, yet their application to Cyber Threat Intelligence (CTI) remains limited. CTI anal…
R+R: Revisiting Static Feature-Based Android Malware Detection using Machine Learning
Md Tanvirul Alam, Dipkamal Bhusal, Nidhi Rastogi
Static feature-based Android malware detection using machine learning (ML) remains critical due to its scalability and efficiency. However, existing approaches often overlook secur…
FACE: Faithful Automatic Concept Extraction
Dipkamal Bhusal, Michael Clifford, Sara Rampazzi +1
Interpreting deep neural networks through concept-based explanations offers a bridge between low-level features and high-level human-understandable semantics. However, existing aut…