Publications (51)
Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and The Way Forward
Adnan Qayyum, Muhammad Usama, Junaid Qadir +1
Connected and autonomous vehicles (CAVs) will form the backbone of future next-generation intelligent transportation systems (ITS) providing travel comfort, road safety, along with…
Analysing the Robustness of Vision-Language-Models to Common Corruptions
Muhammad Usama, Syeda Aishah Asim, Syed Bilal Ali +2
Vision-language models (VLMs) have demonstrated impressive capabilities in understanding and reasoning about visual and textual content. However, their robustness to common image c…
Sparks of Large Audio Models: A Survey and Outlook
Siddique Latif, Moazzam Shoukat, Fahad Shamshad +8
This survey paper provides a comprehensive overview of the recent advancements and challenges in applying large language models to the field of audio signal processing. Audio proce…
Memory-Augmented Architecture for Long-Term Context Handling in Large Language Models
Haseeb Ullah Khan Shinwari, Muhammad Usama
Large Language Models face significant challenges in maintaining coherent interactions over extended dialogues due to their limited contextual memory. This limitation often leads t…
A First Look at COVID-19 Messages on WhatsApp in Pakistan
R. Tallal Javed, Mirza Elaaf Shuja, Muhammad Usama +5
The worldwide spread of COVID-19 has prompted extensive online discussions, creating an `infodemic' on social media platforms such as WhatsApp and Twitter. However, the information…
NURBGen: High-Fidelity Text-to-CAD Generation through LLM-Driven NURBS Modeling
Muhammad Usama, Mohammad Sadil Khan, Didier Stricker +1
Generating editable 3D CAD models from natural language remains challenging, as existing text-to-CAD systems either produce meshes or rely on scarce design-history data. We present…
Design of a six wheel suspension and a three-axis linear actuation mechanism for a laser weeding robot
Muhammad Usama, Muhammad Ibrahim Khan, Ahmad Hasan +5
Mobile robots are increasingly utilized in agriculture to automate labor-intensive tasks such as weeding, sowing, harvesting and soil analysis. Recently, agricultural robots have b…
Action Segmentation Using 2D Skeleton Heatmaps and Multi-Modality Fusion
Syed Waleed Hyder, Muhammad Usama, Anas Zafar +5
This paper presents a 2D skeleton-based action segmentation method with applications in fine-grained human activity recognition. In contrast with state-of-the-art methods which dir…
EnergyFormer: Energy Attention with Fourier Embedding for Hyperspectral Image Classification
Saad Sohail, Muhammad Usama, Usman Ghous +3
Hyperspectral imaging (HSI) provides rich spectral-spatial information across hundreds of contiguous bands, enabling precise material discrimination in applications such as environ…
Learning-Driven Exploration for Reinforcement Learning
Muhammad Usama, Dong Eui Chang
Effective and intelligent exploration has been an unresolved problem for reinforcement learning. Most contemporary reinforcement learning relies on simple heuristic strategies such…
AI-Based Emotion Recognition: Promise, Peril, and Prescriptions for Prosocial Path
Siddique Latif, Hafiz Shehbaz Ali, Muhammad Usama +3
Automated emotion recognition (AER) technology can detect humans' emotional states in real-time using facial expressions, voice attributes, text, body movements, and neurological s…
MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation
Sankalp Sinha, Mohammad Sadil Khan, Muhammad Usama +4
Generating high-fidelity 3D content from text prompts remains a significant challenge in computer vision due to the limited size, diversity, and annotation depth of the existing da…
Privacy Enhancement for Cloud-Based Few-Shot Learning
Archit Parnami, Muhammad Usama, Liyue Fan +1
Requiring less data for accurate models, few-shot learning has shown robustness and generality in many application domains. However, deploying few-shot models in untrusted environm…
Adversarial Attacks on Cognitive Self-Organizing Networks: The Challenge and the Way Forward
Muhammad Usama, Junaid Qadir, Ala Al-Fuqaha
Future communications and data networks are expected to be largely cognitive self-organizing networks (CSON). Such networks will have the essential property of cognitive self-organ…
Hybrid State-Space and GRU-based Graph Tokenization Mamba for Hyperspectral Image Classification
Muhammad Ahmad, Muhammad Hassaan Farooq Butt, Muhammad Usama +4
Hyperspectral image (HSI) classification plays a pivotal role in domains such as environmental monitoring, agriculture, and urban planning. However, it faces significant challenges…
WaveMamba: Spatial-Spectral Wavelet Mamba for Hyperspectral Image Classification
Muhammad Ahmad, Muhammad Usama, Manuel Mazzara +1
Hyperspectral Imaging (HSI) has proven to be a powerful tool for capturing detailed spectral and spatial information across diverse applications. Despite the advancements in Deep L…
Vector Control Algorithm Based on Different Current Control Switching Techniques for Ac Motor Drives
Muhammad Usama, Jaehong Kim
A comparative analysis of vector control scheme based on different current control switching pulses (HC, SPWM, DPWM and SVPWM) for the speed response of motor drive is analysed in…
Robotic Navigation using Entropy-Based Exploration
Muhammad Usama, Dong Eui Chang
Robotic navigation concerns the task in which a robot should be able to find a safe and feasible path and traverse between two points in a complex environment. We approach the prob…
Caveat emptor: the risks of using big data for human development
Siddique Latif, Adnan Qayyum, Muhammad Usama +3
Big data revolution promises to be instrumental in facilitating sustainable development in many sectors of life such as education, health, agriculture, and in combating humanitaria…
Multi-head Spatial-Spectral Mamba for Hyperspectral Image Classification
Muhammad Ahmad, Muhammad Hassaan Farooq Butt, Muhammad Usama +3
Spatial-Spectral Mamba (SSM) improves computational efficiency and captures long-range dependencies, addressing Transformer limitations. However, traditional Mamba models overlook…
Convergence Without Understanding: When Language Models Agree on Representations but Disagree on Reasoning
Muhammad Usama, Dong Eui Chang
Large language models trained under diverse objectives and architectures have been shown to develop increasingly similar internal representations, an observation formalized as the…
Adversarial Machine Learning Attack on Modulation Classification
Muhammad Usama, Muhammad Asim, Junaid Qadir +2
Modulation classification is an important component of cognitive self-driving networks. Recently many ML-based modulation classification methods have been proposed. We have evaluat…
Towards Robust Neural Networks with Lipschitz Continuity
Muhammad Usama, Dong Eui Chang
Deep neural networks have shown remarkable performance across a wide range of vision-based tasks, particularly due to the availability of large-scale datasets for training and bett…
On Analyzing Self-Driving Networks: A Systems Thinking Approach
Touseef Yaqoob, Muhammad Usama, Junaid Qadir +1
The networking field has recently started to incorporate artificial intelligence (AI), machine learning (ML), big data analytics combined with advances in networking (such as softw…
Real Time Headway Predictions in Urban Rail Systems and Implications for Service Control: A Deep Learning Approach
Muhammad Usama, Haris Koutsopoulos
Efficient real-time dispatching in urban metro systems is essential for ensuring service reliability, maximizing resource utilization, and improving passenger satisfaction. This st…
Emotions Beyond Words: Non-Speech Audio Emotion Recognition With Edge Computing
Ibrahim Malik, Siddique Latif, Sanaullah Manzoor +3
Non-speech emotion recognition has a wide range of applications including healthcare, crime control and rescue, and entertainment, to name a few. Providing these applications using…
Estimating City-wide Operating Mode Distribution of Light-Duty Vehicles: A Neural Network-based Approach
Muhammad Usama, Haris N. Koutsopoulos, Zhengbing He +1
Driving cycles are a set of driving conditions and are crucial for the existing emission estimation model to evaluate vehicle performance, fuel efficiency, and emissions, by matchi…
Generative VS non-Generative Models in Engineering Shape Optimization
Muhammad Usama, Zahid Masood, Shahroz Khan +2
In this work, we perform a systematic comparison of the effectiveness and efficiency of generative and non-generative models in constructing design spaces for novel and efficient d…
Examining Machine Learning for 5G and Beyond through an Adversarial Lens
Muhammad Usama, Rupendra Nath Mitra, Inaam Ilahi +2
Spurred by the recent advances in deep learning to harness rich information hidden in large volumes of data and to tackle problems that are hard to model/solve (e.g., resource allo…
Distributional Reinforcement Learning with Information Bottleneck for Uncertainty-Aware DRAM Equalization
Muhammad Usama, Dong Eui Chang
Equalizer parameter optimization is critical for signal integrity in high-speed memory systems operating at multi-gigabit data rates. However, existing methods suffer from computat…
Fake Visual Content Detection Using Two-Stream Convolutional Neural Networks
Bilal Yousaf, Muhammad Usama, Waqas Sultani +2
Rapid progress in adversarial learning has enabled the generation of realistic-looking fake visual content. To distinguish between fake and real visual content, several detection t…
ARD-LoRA: Dynamic Rank Allocation for Parameter-Efficient Fine-Tuning of Foundation Models with Heterogeneous Adaptation Needs
Haseeb Ullah Khan Shinwari, Muhammad Usama
Conventional Low-Rank Adaptation (LoRA) methods employ a fixed rank, imposing uniform adaptation across transformer layers and attention heads despite their heterogeneous learning…
Estimating link level traffic emissions: enhancing MOVES with open-source data
Lijiao Wang, Muhammad Usama, Haris N. Koutsopoulos +1
Open-source data offers a scalable and transparent foundation for estimating vehicle activity and emissions in urban regions. In this study, we propose a data-driven framework that…
The Adversarial Machine Learning Conundrum: Can The Insecurity of ML Become The Achilles' Heel of Cognitive Networks?
Muhammad Usama, Junaid Qadir, Ala Al-Fuqaha +1
The holy grail of networking is to create \textit{cognitive networks} that organize, manage, and drive themselves. Such a vision now seems attainable thanks in large part to the pr…
Vehicle and License Plate Recognition with Novel Dataset for Toll Collection
Muhammad Usama, Hafeez Anwar, Abbas Anwar +1
We propose an automatic framework for toll collection, consisting of three steps: vehicle type recognition, license plate localization, and reading. However, each of the three step…
Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design
Elias Berger, Muhammad Usama, Jan Mehlstäubl +2
Large Language Models (LLMs) can generate Computer-Aided Design (CAD), yet lack physical comprehension required for reliable engineering design. Instead of attempting to implicitly…
Physics-Informed Geometric Operators to Support Surrogate, Dimension Reduction and Generative Models for Engineering Design
Shahroz Khan, Zahid Masood, Muhammad Usama +4
In this work, we propose a set of physics-informed geometric operators (GOs) to enrich the geometric data provided for training surrogate/discriminative models, dimension reduction…
AI-driven, Model-Free Current Control: A Deep Symbolic Approach for Optimal Induction Machine Performance
Muhammad Usama, Yunkyung Hwang, Jaehong Kim
This paper proposed a straightforward and efficient current control solution for induction machines employing deep symbolic regression (DSR). The proposed DSR-based control design…
Adversarial ML Attack on Self Organizing Cellular Networks
Salah-ud-din Farooq, Muhammad Usama, Junaid Qadir +1
Deep Neural Networks (DNN) have been widely adopted in self-organizing networks (SON) for automating different networking tasks. Recently, it has been shown that DNN lack robustnes…
Deep Reinforcement Learning-Based DRAM Equalizer Parameter Optimization Using Latent Representations
Muhammad Usama, Dong Eui Chang
Equalizer parameter optimization for signal integrity in high-speed Dynamic Random Access Memory systems is crucial but often computationally demanding or model-reliant. This paper…
DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces
Mohammad Sadil Khan, Muhammad Usama, Rolandos Alexandros Potamias +4
Computer-Aided Design (CAD) relies on structured and editable geometric representations, yet existing generative methods are constrained by small annotated datasets with explicit d…
Can Large Language Models Aid in Annotating Speech Emotional Data? Uncovering New Frontiers
Siddique Latif, Muhammad Usama, Mohammad Ibrahim Malik +1
Despite recent advancements in speech emotion recognition (SER) models, state-of-the-art deep learning (DL) approaches face the challenge of the limited availability of annotated d…
Black-box Adversarial ML Attack on Modulation Classification
Muhammad Usama, Junaid Qadir, Ala Al-Fuqaha
Recently, many deep neural networks (DNN) based modulation classification schemes have been proposed in the literature. We have evaluated the robustness of two famous such modulati…
Intelligent Resource Allocation in Dense LoRa Networks using Deep Reinforcement Learning
Inaam Ilahi, Muhammad Usama, Muhammad Omer Farooq +2
The anticipated increase in the count of IoT devices in the coming years motivates the development of efficient algorithms that can help in their effective management while keeping…
BRepCLIP: Contrastive Multimodal Pretraining on BRep Primitives for CAD Understanding
Muhammad Usama, Didier Stricker, Mohammad Sadil Khan +1
Learning representations of CAD models is a largely open problem. While 3D representation learning has flourished around point clouds and meshes, the native format of CAD - boundar…
Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning
Inaam Ilahi, Muhammad Usama, Junaid Qadir +4
Deep Reinforcement Learning (DRL) has numerous applications in the real world thanks to its outstanding ability in quickly adapting to the surrounding environments. Despite its gre…
Artificial Intelligence as an Enabler for Cognitive Self-Organizing Future Networks
Siddiq Latif, Farrukh Pervez, Muhammad Usama +1
The explosive increase in number of smart devices hosting sophisticated applications is rapidly affecting the landscape of information communication technology industry. Mobile sub…
Transformers in Speech Processing: A Survey
Siddique Latif, Aun Zaidi, Heriberto Cuayahuitl +4
The remarkable success of transformers in the field of natural language processing has sparked the interest of the speech-processing community, leading to an exploration of their p…
Spatial and Spatial-Spectral Morphological Mamba for Hyperspectral Image Classification
Muhammad Ahmad, Muhammad Hassaan Farooq Butt, Adil Mehmood Khan +6
Recent advancements in transformers, specifically self-attention mechanisms, have significantly improved hyperspectral image (HSI) classification. However, these models often suffe…
Learning High-Quality Latent Representations for Anomaly Detection and Signal Integrity Enhancement in High-Speed Signals
Muhammad Usama, Hee-Deok Jang, Soham Shanbhag +3
This paper addresses the dual challenge of improving anomaly detection and signal integrity in high-speed dynamic random access memory signals. To achieve this, we propose a joint…
Unsupervised Machine Learning for Networking: Techniques, Applications and Research Challenges
Muhammad Usama, Junaid Qadir, Aunn Raza +5
While machine learning and artificial intelligence have long been applied in networking research, the bulk of such works has focused on supervised learning. Recently there has been…