Tauseef Ahmed

Tauseef Ahmed, Tao Sun, Jeronimo Castrillon et al.

Deep learning has greatly advanced automatic speech recognition (ASR), enabling widespread deployment on edge devices such as smartphones and smart home systems. However, the computational and energy demands of deep neural networks pose significant challenges for such resource-constrained deployments, introducing latency and limiting real-time interaction. Neuromorphic computing offers a promising solution by introducing activation sparsity through spiking neural networks (SNNs) and event-driven neural networks, converting dense operations into sparse computations. However, a study that evaluates the hardware benefits of different neuromorphic strategies remains lacking for ASR. This paper explores spiking and event-driven neuromorphic neural networks to improve activation sparsity in the state-of-the-art SpeechMamba model for ASR. We introduce an event-driven SpeechMamba with FATReLU activation, achieving over 60% activation sparsity with less than 1% accuracy degradation on LibriSpeech. We also propose a spiking SpeechMamba that attains over 70% sparsity while using 30% fewer parameters than comparable SNNs. Finally, we develop a cycle-accurate event-driven simulator enabling flexible algorithm-hardware co-exploration, which helps us identify computational bottlenecks and yields over 10% additional efficiency improvements.

Mohammed Mahir Rahman, Shahzad Memon, Tauseef Ahmed et al.

The rapid advancement of information technology has introduced a noticeable shift from traditional offline practices to more efficient and interconnected online environments. This transition, while offering convenience, has also increased exposure to various cyber threats such as identity theft, impersonation, and phishing scams. Reconnaissance, or briefly known as information gathering, is a key stage for threat actors, often relying on open-source intelligence (OSINT) to collect sensitive and extensive data on targets. In response to this challenge, this study introduces reconCTI, a command-line tool built using Python for Linux systems. The tool is designed to search for sensitive data leaks across both surface web and dark web platforms. It allows users to input specific keywords, scan multiple sites at once, and then assess the findings by referencing the MITRE ATT&CK framework. The results are compiled into a threat report that also includes possible mitigation strategies. reconCTI is intended to support both cybersecurity professionals and individuals in identifying risks early and taking appropriate action.

Amaan Ahmed, Mohammed Mahir Rahman, Shahzad Memon et al.

This paper illustrates the design and implementation of a smart home automation system for the conservation of energy and user control with the help of environmental sensors and Raspberry Pi 5. It monitors real-time conditions like motion, temperature, humidity, light and smoke to automatically control the device's behavior and save energy. A prototype single two-room was developed which uses GPIO/I2C interfaces to integrate sensors and actuators. The fan speed and LED brightness was dynamically controlled using PWM. Manual control and real-time monitoring are made possible through a web dashboard that was developed using Flask and graphical displays, and CSV logs of the energy are taken every 30 seconds. It was designed in an iterative model of sprints and the energy savings during testing was more than 46% over an always-on model. The results prove that with the help of these low-cost, modular devices it is possible to improve sustainability and usability in the home as part of the IoT.

Akhitha Pakala, Mohammed Mahir Rahman, Shahzad Memon et al.

The growing sophistication of GAN-based image manipulation presents significant challenges for digital forensics. This study compares the performance of four pretrained CNN architectures including VGG16, ResNet50, EfficientNetB0, and XceptionNet for fake image detection using a unified preprocessing and training pipeline. A dataset of real and manipulated images was processed through resizing, normalization, and augmentation to address class imbalance and improve generalization. Models were evaluated using Accuracy, Precision, Recall, F1-score, and ROC-AUC. VGG16 achieved the highest accuracy at 91%, with XceptionNet, ResNet50, and EfficientNetB0 each reaching 90%. EfficientNetB0 showed stronger sensitivity to fake images but reduced reliability on real samples, reflecting imbalance-driven bias. Limitations include dataset imbalance, overfitting, and limited interpretability, which affect cross-domain robustness. The study provides a reproducible baseline and underscores the need for balanced datasets, advanced augmentation, and fairness-aware training to develop reliable fake image detection systems.

Asad Ullah, Tauseef Ahmed

Training a code-switching (CS) language model using only monolingual data is still an ongoing research problem. In this paper, a CS language model is trained using only monolingual training data. As recurrent neural network (RNN) models are best suited for predicting sequential data. In this work, an RNN language model is trained using alternate batches from only monolingual English and Spanish data and the perplexity of the language model is computed. From the results, it is concluded that using alternate batches of monolingual data in training reduced the perplexity of a CS language model. The results were consistently improved using mean square error (MSE) in the output embeddings of RNN based language model. By combining both methods, perplexity is reduced from 299.63 to 80.38. The proposed methods were comparable to the language model fine tune with code-switch training data.