arXiv subjects

Muhammad Ali

Publications and source records attributed to Muhammad Ali.

At least 37 records · Page 2Linked to original sources

arXiv2025

X-Cross: Image Encryption Featuring Novel Dual-Layer Block Permutation and Dynamic Substitution Techniques

In this digital age, ensuring the security of digital data, especially the image data is critically important. Image encryption plays an important role in securing the online transmission/storage of images from unauthorized access. In this regard, this paper presents a novel diffusion-confusion-based image encryption algorithm named as X-CROSS. The diffusion phase involves a dual-layer block permutation. It involves a bit-level permutation termed Inter-Bit Transference (IBT) using a Bit-Extraction key, and pixel permutation with a unique X-crosspermutation algorithm to effectively scramble the pixels within an image. The proposed algorithm utilizes a resilient 2D chaotic map with non-linear dynamical behavior, assisting in generating complex Extraction Keys. After the permutation phase, the confusion phase proceeds with a dynamic substitution technique on the permuted images, establishing the final encryption layer. This combination of novel permutation and confusion results in the removal of the image's inherent patterns and increases its resistance to cyber-attacks. The close to ideal statistical security results for information entropy, correlation, homogeneity, contrast, and energy validate the proposed scheme's effectiveness in hiding the information within the image.

cs.CR↗

arXiv2024

Performance Analysis of Traditional and Network Coded Transmission in Infrastructure-less Multi-hop Wireless Networks

Infrastructure-less Multi-hop Wireless Networks are the backbone for mission critical communications such as in disaster and battlefield scenarios. However, interference signals in the wireless channel cause losses to transmission in wireless networks resulting in a reduced network throughput and making efficient transmission very challenging. Therefore, techniques to overcome interference and increase transmission efficiency have been a hot area of research for decades. In this paper two methods for transmitting data through infrastructure-less multi hop wireless networks, Traditional (TR) and Network Coded (NC) transmission are thoroughly examined for scenarios having one or two communication streams in a network. The study has developed network models in MATLAB for each transmission technique and scenario. The simulation results showed that the NC transmission method yielded a better throughput under the same network settings and physical interference. Furthermore, the impact of increasing numbers of hops between source and destination on the network capacity and the communications latency was also observed and conclusions were drawn.

cs.NI↗

arXiv2024

COSNet: A Novel Semantic Segmentation Network using Enhanced Boundaries in Cluttered Scenes

Automated waste recycling aims to efficiently separate the recyclable objects from the waste by employing vision-based systems. However, the presence of varying shaped objects having different material types makes it a challenging problem, especially in cluttered environments. Existing segmentation methods perform reasonably on many semantic segmentation datasets by employing multi-contextual representations, however, their performance is degraded when utilized for waste object segmentation in cluttered scenarios. In addition, plastic objects further increase the complexity of the problem due to their translucent nature. To address these limitations, we introduce an efficacious segmentation network, named COSNet, that uses boundary cues along with multi-contextual information to accurately segment the objects in cluttered scenes. COSNet introduces novel components including feature sharpening block (FSB) and boundary enhancement module (BEM) for enhancing the features and highlighting the boundary information of irregular waste objects in cluttered environment. Extensive experiments on three challenging datasets including ZeroWaste-f, SpectralWaste, and ADE20K demonstrate the effectiveness of the proposed method. Our COSNet achieves a significant gain of 1.8% on ZeroWaste-f and 2.1% on SpectralWaste datasets respectively in terms of mIoU metric.

cs.CV↗

arXiv2024

Underwater Object Detection Enhancement via Channel Stabilization

The complex marine environment exacerbates the challenges of object detection manifold. Marine trash endangers the aquatic ecosystem, presenting a persistent challenge. Accurate detection of marine deposits is crucial for mitigating this harm. Our work addresses underwater object detection by enhancing image quality and evaluating detection methods. We use Detectron2's backbone with various base models and configurations for this task. We propose a novel channel stabilization technique alongside a simplified image enhancement model to reduce haze and color cast in training images, improving multi-scale object detection. Following image processing, we test different Detectron2 backbones for optimal detection accuracy. Additionally, we apply a sharpening filter with augmentation techniques to highlight object profiles for easier recognition. Results are demonstrated on the TrashCan Dataset, both instance and material versions. The best-performing backbone method incorporates our channel stabilization and augmentation techniques. We also compare our Detectron2 detection results with the Deformable Transformer. In the instance version of TrashCan 1.0, our method achieves a 9.53% absolute increase in average precision for small objects and a 7% absolute gain in bounding box detection compared to the baseline. The code will be available on Code: https://github.com/aliman80/Underwater- Object-Detection-via-Channel-Stablization

cs.CV↗

arXiv2024

Understanding the Interplay of Scale, Data, and Bias in Language Models: A Case Study with BERT

In the current landscape of language model research, larger models, larger datasets and more compute seems to be the only way to advance towards intelligence. While there have been extensive studies of scaling laws and models' scaling behaviors, the effect of scale on a model's social biases and stereotyping tendencies has received less attention. In this study, we explore the influence of model scale and pre-training data on its learnt social biases. We focus on BERT -- an extremely popular language model -- and investigate biases as they show up during language modeling (upstream), as well as during classification applications after fine-tuning (downstream). Our experiments on four architecture sizes of BERT demonstrate that pre-training data substantially influences how upstream biases evolve with model scale. With increasing scale, models pre-trained on large internet scrapes like Common Crawl exhibit higher toxicity, whereas models pre-trained on moderated data sources like Wikipedia show greater gender stereotypes. However, downstream biases generally decrease with increasing model scale, irrespective of the pre-training data. Our results highlight the qualitative role of pre-training data in the biased behavior of language models, an often overlooked aspect in the study of scale. Through a detailed case study of BERT, we shed light on the complex interplay of data and model scale, and investigate how it translates to concrete biases.

cs.CL↗

arXiv2024

FANet: Feature Amplification Network for Semantic Segmentation in Cluttered Background

Existing deep learning approaches leave out the semantic cues that are crucial in semantic segmentation present in complex scenarios including cluttered backgrounds and translucent objects, etc. To handle these challenges, we propose a feature amplification network (FANet) as a backbone network that incorporates semantic information using a novel feature enhancement module at multi-stages. To achieve this, we propose an adaptive feature enhancement (AFE) block that benefits from both a spatial context module (SCM) and a feature refinement module (FRM) in a parallel fashion. SCM aims to exploit larger kernel leverages for the increased receptive field to handle scale variations in the scene. Whereas our novel FRM is responsible for generating semantic cues that can capture both low-frequency and high-frequency regions for better segmentation tasks. We perform experiments over challenging real-world ZeroWaste-f dataset which contains background-cluttered and translucent objects. Our experimental results demonstrate the state-of-the-art performance compared to existing methods.

cs.CV↗

arXiv2024

CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned Representation

Multi-label classification is an essential task utilized in a wide variety of real-world applications. Multi-label zero-shot learning is a method for classifying images into multiple unseen categories for which no training data is available, while in general zero-shot situations, the test set may include observed classes. The CLIP-Decoder is a novel method based on the state-of-the-art ML-Decoder attention-based head. We introduce multi-modal representation learning in CLIP-Decoder, utilizing the text encoder to extract text features and the image encoder for image feature extraction. Furthermore, we minimize semantic mismatch by aligning image and word embeddings in the same dimension and comparing their respective representations using a combined loss, which comprises classification loss and CLIP loss. This strategy outperforms other methods and we achieve cutting-edge results on zero-shot multilabel classification tasks using CLIP-Decoder. Our method achieves an absolute increase of 3.9% in performance compared to existing methods for zero-shot learning multi-label classification tasks. Additionally, in the generalized zero-shot learning multi-label classification task, our method shows an impressive increase of almost 2.3%.

cs.CV↗

arXiv2023

Unraveling Forward and Backward Source Problems for a Nonlocal Integrodifferential Equation: A Journey through Operational Calculus for Dzherbashian-Nersesian Operator

This article primarily aims at introducing a novel operational calculus of Mikusiński's type for the Dzherbashian-Nersesian operator. Using this calculus, we are able to derive exact solutions for the forward and backward source problems (BSPs) of a differential equation that features Dzherbashian-Nersesian operator in time and intertwined with nonlocal boundary conditions. The initial condition is expressed in terms of Riemann-Liouville integral (RLI). Solution is presented using Mittag-Leffler type functions (MLTFs). The outcomes related to the existence and uniqueness subject to certain conditions of regularity on the input data are established.

math.AP↗

arXiv2023

Problematic Advertising and its Disparate Exposure on Facebook

Targeted advertising remains an important part of the free web browsing experience, where advertisers' targeting and personalization algorithms together find the most relevant audience for millions of ads every day. However, given the wide use of advertising, this also enables using ads as a vehicle for problematic content, such as scams or clickbait. Recent work that explores people's sentiments toward online ads, and the impacts of these ads on people's online experiences, has found evidence that online ads can indeed be problematic. Further, there is the potential for personalization to aid the delivery of such ads, even when the advertiser targets with low specificity. In this paper, we study Facebook -- one of the internet's largest ad platforms -- and investigate key gaps in our understanding of problematic online advertising: (a) What categories of ads do people find problematic? (b) Are there disparities in the distribution of problematic ads to viewers? and if so, (c) Who is responsible -- advertisers or advertising platforms? To answer these questions, we empirically measure a diverse sample of user experiences with Facebook ads via a 3-month longitudinal panel. We categorize over 32,000 ads collected from this panel ($n=132$); and survey participants' sentiments toward their own ads to identify four categories of problematic ads. Statistically modeling the distribution of problematic ads across demographics, we find that older people and minority groups are especially likely to be shown such ads. Further, given that 22% of problematic ads had no specific targeting from advertisers, we infer that ad delivery algorithms (advertising platforms themselves) played a significant role in the biased distribution of these ads.

cs.CY↗

arXiv2022

Scalable Organic Semiconductor Neutron Detectors

A long-standing limitation of semiconductor neutron detectors is the lack of a scalable solution to make large area instruments. Neutron detectors are used in a wide range of applications, including the nuclear industry, safeguarding radioactive material, neutron imaging, non-destructive testing, understanding space weather effects on commercial electronics used in aviation, and for fundamental science such as nuclear and particle physics. Here we demonstrate that a solution processed organic semiconductor technology, which is scalable, can solve this aproblem. We have demonstrated detection of fast neutrons from monoenergetic beams (energies 0.565 and 16.5 MeV), from AmBe sources, and thermal energy (0.025 eV) in devices sensitised with B-10 enriched B_4C. This energy range is of interest for many of the applications listed above. The detector response is found to be linear with flux up to 1.5 x 10^7 n/cm^2/s. As organic semiconductors are a similar density to human tissue, this technology may be of interest for medical physics applications, for example B neutron capture therapy dose monitoring and understanding neutron interactions in human tissue.

physics.ins-det↗

arXiv2022

Vision Transformers in Medical Computer Vision -- A Contemplative Retrospection

Recent escalation in the field of computer vision underpins a huddle of algorithms with the magnificent potential to unravel the information contained within images. These computer vision algorithms are being practised in medical image analysis and are transfiguring the perception and interpretation of Imaging data. Among these algorithms, Vision Transformers are evolved as one of the most contemporary and dominant architectures that are being used in the field of computer vision. These are immensely utilized by a plenty of researchers to perform new as well as former experiments. Here, in this article we investigate the intersection of Vision Transformers and Medical images and proffered an overview of various ViTs based frameworks that are being used by different researchers in order to decipher the obstacles in Medical Computer Vision. We surveyed the application of Vision transformers in different areas of medical computer vision such as image-based disease classification, anatomical structure segmentation, registration, region-based lesion Detection, captioning, report generation, reconstruction using multiple medical imaging modalities that greatly assist in medical diagnosis and hence treatment process. Along with this, we also demystify several imaging modalities used in Medical Computer Vision. Moreover, to get more insight and deeper understanding, self-attention mechanism of transformers is also explained briefly. Conclusively, we also put some light on available data sets, adopted methodology, their performance measures, challenges and their solutions in form of discussion. We hope that this review article will open future directions for researchers in medical computer vision.

eess.IV↗

arXiv2022

Survey on Self-supervised Representation Learning Using Image Transformations

Deep neural networks need huge amount of training data, while in real world there is a scarcity of data available for training purposes. To resolve these issues, self-supervised learning (SSL) methods are used. SSL using geometric transformations (GT) is a simple yet powerful technique used in unsupervised representation learning. Although multiple survey papers have reviewed SSL techniques, there is none that only focuses on those that use geometric transformations. Furthermore, such methods have not been covered in depth in papers where they are reviewed. Our motivation to present this work is that geometric transformations have shown to be powerful supervisory signals in unsupervised representation learning. Moreover, many such works have found tremendous success, but have not gained much attention. We present a concise survey of SSL approaches that use geometric transformations. We shortlist six representative models that use image transformations including those based on predicting and autoencoding transformations. We review their architecture as well as learning methodologies. We also compare the performance of these models in the object recognition task on CIFAR-10 and ImageNet datasets. Our analysis indicates the AETv2 performs the best in most settings. Rotation with feature decoupling also performed well in some settings. We then derive insights from the observed results. Finally, we conclude with a summary of the results and insights as well as highlighting open problems to be addressed and indicating various future directions.

cs.CV↗

arXiv2022

TransformNet: Self-supervised representation learning through predicting geometric transformations

Deep neural networks need a big amount of training data, while in the real world there is a scarcity of data available for training purposes. To resolve this issue unsupervised methods are used for training with limited data. In this report, we describe the unsupervised semantic feature learning approach for recognition of the geometric transformation applied to the input data. The basic concept of our approach is that if someone is unaware of the objects in the images, he/she would not be able to quantitatively predict the geometric transformation that was applied to them. This self supervised scheme is based on pretext task and the downstream task. The pretext classification task to quantify the geometric transformations should force the CNN to learn high-level salient features of objects useful for image classification. In our baseline model, we define image rotations by multiples of 90 degrees. The CNN trained on this pretext task will be used for the classification of images in the CIFAR-10 dataset as a downstream task. we run the baseline method using various models, including ResNet, DenseNet, VGG-16, and NIN with a varied number of rotations in feature extracting and fine-tuning settings. In extension of this baseline model we experiment with transformations other than rotation in pretext task. We compare performance of selected models in various settings with different transformations applied to images,various data augmentation techniques as well as using different optimizers. This series of different type of experiments will help us demonstrate the recognition accuracy of our self-supervised model when applied to a downstream task of classification.

cs.CV↗

arXiv2022

Inverse problem for recovery of temporal component of source term for multi-term time fractional parabolic equation with nonlocal boundary datum

Inverse problem for multi-term fractional parabolic equation in two dimensional space, involving m + 1 Caputo fractional derivatives in time, is investigated. Presence of nonlocal boundary conditions leads to a non-self-adjoint spectral problem. A bi-orthogonal system of functions is used to construct the solution that involves double infinite series. Properties of multinomial Mittag-Leffler function and eigenfunctions are used to prove the classical nature of the solution under certain regularity conditions on the given datum.

math.AP↗

arXiv2022

SubOmiEmbed: Self-supervised Representation Learning of Multi-omics Data for Cancer Type Classification

For personalized medicines, very crucial intrinsic information is present in high dimensional omics data which is difficult to capture due to the large number of molecular features and small number of available samples. Different types of omics data show various aspects of samples. Integration and analysis of multi-omics data give us a broad view of tumours, which can improve clinical decision making. Omics data, mainly DNA methylation and gene expression profiles are usually high dimensional data with a lot of molecular features. In recent years, variational autoencoders (VAE) have been extensively used in embedding image and text data into lower dimensional latent spaces. In our project, we extend the idea of using a VAE model for low dimensional latent space extraction with the self-supervised learning technique of feature subsetting. With VAEs, the key idea is to make the model learn meaningful representations from different types of omics data, which could then be used for downstream tasks such as cancer type classification. The main goals are to overcome the curse of dimensionality and integrate methylation and expression data to combine information about different aspects of same tissue samples, and hopefully extract biologically relevant features. Our extension involves training encoder and decoder to reconstruct the data from just a subset of it. By doing this, we force the model to encode most important information in the latent representation. We also added an identity to the subsets so that the model knows which subset is being fed into it during training and testing. We experimented with our approach and found that SubOmiEmbed produces comparable results to the baseline OmiEmbed with a much smaller network and by using just a subset of the data. This work can be improved to integrate mutation-based genomic data as well.

cs.LG↗

arXiv2021

A proactive malicious software identification approach for digital forensic examiners

Digital investigators often get involved with cases, which seemingly point the responsibility to the person to which the computer belongs, but after a thorough examination malware is proven to be the cause, causing loss of precious time. Whilst Anti-Virus (AV) software can assist the investigator in identifying the presence of malware, with the increase in zero-day attacks and errors that exist in AV tools, this is something that cannot be relied upon. The aim of this paper is to investigate the behaviour of malware upon various Windows operating system versions in order to determine and correlate the relationship between malicious software and OS artifacts. This will enable an investigator to be more efficient in identifying the presence of new malware and provide a starting point for further investigation.

cs.CR↗

arXiv2021

Inverse problems for diffusion equation with fractional Dzherbashian-Nersesian operator

Fractional Dzherbashian-Nersesian operator is considered and three famous fractional order derivatives namely Riemann-Liouville, Caputo and Hilfer derivatives are shown to be special cases of the earlier one. The expression for Laplace transform of fractional Dzherbashian-Nersesian operator is constructed. Inverse problems of recovering space dependent and time dependent source terms of a time fractional diffusion equation with involution and involving fractional Dzherbashian-Nersesian operator are considered. The results on existence and uniqueness for the solutions of inverse problems are established. The results obtained here generalize several known results.

math.AP↗

arXiv2020

Malware Classification using Deep Learning based Feature Extraction and Wrapper based Feature Selection Technique

In the case of malware analysis, categorization of malicious files is an essential part after malware detection. Numerous static and dynamic techniques have been reported so far for categorizing malware. This research presents a deep learning-based malware detection (DLMD) technique based on static methods for classifying different malware families. The proposed DLMD technique uses both the byte and ASM files for feature engineering, thus classifying malware families. First, features are extracted from byte files using two different Deep Convolutional Neural Networks (CNN). After that, essential and discriminative opcode features are selected using a wrapper-based mechanism, where Support Vector Machine (SVM) is used as a classifier. The idea is to construct a hybrid feature space by combining the different feature spaces to overcome the shortcoming of particular feature space and thus, reduce the chances of missing a malware. Finally, the hybrid feature space is used to train a Multilayer Perceptron, which classifies all nine different malware families. Experimental results show that proposed DLMD technique achieves log-loss of 0.09 for ten independent runs. Moreover, the proposed DLMD technique's performance is compared against different classifiers and shows its effectiveness in categorizing malware. The relevant code and database can be found at https://github.com/cyberhunters/Malware-Detection-Using-Machine-Learning.

cs.CR↗