8 citations · 18 across the 20 of their papers we have counts for
20 papers
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…
Minerva: Reinforcement Learning with Verifiable Rewards for Cyber Threat Intelligence LLMs
Md Tanvirul Alam, Aritran Piplai, Ionut Cardei +2
Cyber threat intelligence (CTI) analysts routinely convert noisy, unstructured security artifacts into standardized, automation-ready representations. Although large language model…
Limits of Generalization in RLVR: Two Case Studies in Mathematical Reasoning
Md Tanvirul Alam, Nidhi Rastogi
Mathematical reasoning is a central challenge for large language models (LLMs), requiring not only correct answers but also faithful reasoning processes. Reinforcement Learning wit…
SPHINX: A Synthetic Environment for Visual Perception and Reasoning
Md Tanvirul Alam, Saksham Aggarwal, Justin Yang Chae +1
We present Sphinx, a synthetic environment for visual perception and reasoning that targets core cognitive primitives. Sphinx procedurally generates puzzles using motifs, tiles, ch…
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…
Adapting Large Language Models to Emerging Cybersecurity using Retrieval Augmented Generation
Arnabh Borah, Md Tanvirul Alam, Nidhi Rastogi
Security applications are increasingly relying on large language models (LLMs) for cyber threat detection; however, their opaque reasoning often limits trust, particularly in decis…
Towards Understanding Self-play for LLM Reasoning
Justin Yang Chae, Md Tanvirul Alam, Nidhi Rastogi
Recent advances in large language model (LLM) reasoning, led by reinforcement learning with verifiable rewards (RLVR), have inspired self-play post-training, where models improve b…
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…
Concept-Based Masking: A Patch-Agnostic Defense Against Adversarial Patch Attacks
Ayushi Mehrotra, Derek Peng, Dipkamal Bhusal +1
Adversarial patch attacks pose a practical threat to deep learning models by forcing targeted misclassifications through localized perturbations, often realized in the physical wor…
Do Sparse Subnetworks Exhibit Cognitively Aligned Attention? Effects of Pruning on Saliency Map Fidelity, Sparsity, and Concept Coherence
Sanish Suwal, Dipkamal Bhusal, Michael Clifford +1
Prior works have shown that neural networks can be heavily pruned while preserving performance, but the impact of pruning on model interpretability remains unclear. In this work, w…
Smaller is Better: Enhancing Transparency in Vehicle AI Systems via Pruning
Sanish Suwal, Shaurya Garg, Dipkamal Bhusal +2
Connected and autonomous vehicles continue to heavily rely on AI systems, where transparency and security are critical for trust and operational safety. Post-hoc explanations provi…
Learning to Look: Cognitive Attention Alignment with Vision-Language Models
Ryan L. Yang, Dipkamal Bhusal, Nidhi Rastogi
Convolutional Neural Networks (CNNs) frequently "cheat" by exploiting superficial correlations, raising concerns about whether they make predictions for the right reasons. Inspired…
ADAPT: A Pseudo-labeling Approach to Combat Concept Drift in Malware Detection
Md Tanvirul Alam, Aritran Piplai, Nidhi Rastogi
Machine learning models are commonly used for malware classification; however, they suffer from performance degradation over time due to concept drift. Adapting these models to cha…
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…
Actionable Cyber Threat Intelligence using Knowledge Graphs and Large Language Models
Romy Fieblinger, Md Tanvirul Alam, Nidhi Rastogi
Cyber threats are constantly evolving. Extracting actionable insights from unstructured Cyber Threat Intelligence (CTI) data is essential to guide cybersecurity decisions. Increasi…
CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligence
Md Tanvirul Alam, Dipkamal Bhusal, Le Nguyen +1
Cyber threat intelligence (CTI) is crucial in today's cybersecurity landscape, providing essential insights to understand and mitigate the ever-evolving cyber threats. The recent r…
SECURE: Benchmarking Large Language Models for Cybersecurity
Dipkamal Bhusal, Md Tanvirul Alam, Le Nguyen +7
Large Language Models (LLMs) have demonstrated potential in cybersecurity applications but have also caused lower confidence due to problems like hallucinations and a lack of truth…
PASA: Attack Agnostic Unsupervised Adversarial Detection using Prediction & Attribution Sensitivity Analysis
Dipkamal Bhusal, Md Tanvirul Alam, Monish K. Veerabhadran +3
Deep neural networks for classification are vulnerable to adversarial attacks, where small perturbations to input samples lead to incorrect predictions. This susceptibility, combin…
MORPH: Towards Automated Concept Drift Adaptation for Malware Detection
Md Tanvirul Alam, Romy Fieblinger, Ashim Mahara +1
Concept drift is a significant challenge for malware detection, as the performance of trained machine learning models degrades over time, rendering them impractical. While prior re…