7 papers
Learning to Transmit: Volatility-Aware Predictive Communication for Energy-Efficient IoT Networks
John Kangethe, Ifrat Ikhtear Uddin, Longwei Wang
Communication is the dominant source of energy consumption in Internet-of-Things (IoT) networks, yet many sensed measurements exhibit strong temporal correlations and provide littl…
Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs
Anupam Wagle, Ifrat Ikhtear Uddin, Chaowei Zhang +1
Large language models (LLMs) exhibit remarkable capabilities but remain highly vulnerable to adversarial prompts and jailbreak attacks. Existing approaches primarily analyze these…
Explainable Novel Category Discovery in Semantic Concept Space
Ifrat Ikhtear Uddin, Yang Zhou, KC Santosh +1
Novel category discovery aims to identify unseen classes from unlabeled data by transferring knowledge from labeled categories, but most existing methods perform discovery in opaqu…
Learning to Select Like Humans: Explainable Active Learning for Medical Imaging
Ifrat Ikhtear Uddin, Longwei Wang, Xiao Qin +2
Medical image analysis requires substantial labeled data for model training, yet expert annotation is expensive and time-consuming. Active learning (AL) addresses this challenge by…
Expert-Guided Explainable Few-Shot Learning with Active Sample Selection for Medical Image Analysis
Longwei Wang, Ifrat Ikhtear Uddin, KC Santosh
Medical image analysis faces two critical challenges: scarcity of labeled data and lack of model interpretability, both hindering clinical AI deployment. Few-shot learning (FSL) ad…
Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness
Longwei Wang, Ifrat Ikhtear Uddin, KC Santosh +3
Adversarial examples reveal critical vulnerabilities in deep neural networks by exploiting their sensitivity to imperceptible input perturbations. While adversarial training remain…