- Advanced Malware Detection Techniques
- Network Security and Intrusion Detection
- Anomaly Detection Techniques and Applications
- Software Testing and Debugging Techniques
- Digital and Cyber Forensics
- Advanced Neural Network Applications
- Software-Defined Networks and 5G
- Software System Performance and Reliability
- Model Reduction and Neural Networks
- Fire Detection and Safety Systems
- Adversarial Robustness in Machine Learning
- Human Mobility and Location-Based Analysis
- Information and Cyber Security
- IoT and Edge/Fog Computing
- IPv6, Mobility, Handover, Networks, Security
- Text and Document Classification Technologies
- Internet Traffic Analysis and Secure E-voting
- Rough Sets and Fuzzy Logic
- Bacillus and Francisella bacterial research
- IoT-based Smart Home Systems
- Blockchain Technology Applications and Security
- Generative Adversarial Networks and Image Synthesis
- Multi-Criteria Decision Making
- Cloud Data Security Solutions
National University of Sciences and Technology
2020-2023
University of the Sciences
2023
Pennsylvania State University
2019
Abstract Enterprises are striving to remain protected against malware-based cyber-attacks on their infrastructure, facilities, networks and systems. Static analysis is an effective approach detect the malware, i.e., malicious Portable Executable (PE). It performs in-depth of PE files without executing, which highly useful minimize risk contaminating system. Yet, instant detection using static has become very difficult due exponential rise in volume variety malware. The compelling need early...
The recent emerging advancements in the domain of fuzzy sets are framework T-spherical set (TSFS) and interval valued (IVTSFS). Keeping view promising significance latest research trend enabling impact IVTSFS, we proposed a novel for decision assembly using TSFS based upon encompassing four impressive dimensions human judgement including favor, abstinence, disfavor, refusal degree. Another remarkable contribution is optimization information modeling prevention loss by redefining concept each...
Enterprises are facing information security threats to intranet-based infrastructure and allied systems from external as well insider cyber actors. A lot of research has been done identify the evil insiders prevent their malicious acts. Moreover, there many others challenges such limited availability real labeled data, variations in organizational nature emerging zero-day attempts insiders. Therefore, new approaches essentially required combat Information Security (IS) non-complaint behavior...
With the expansion in notoriety of modern technology, cyber-attacks have also increased. Traditional techniques to distinguish between malware and benign files are usually signature-based or behavior-based; following methods can be less accurate resource hungry. A robust technique is needed which more efficient takes time as compared traditional techniques. Machine learning play an important role this scenario due its predictive capabilities based upon training. In study, we use existing...
In recent years, VoIP (Voice over Internet Protocol) has emerged as cheap telephony medium for a long distance international and domestic calls. The number of unwanted calls from telemarketers scammers also risen recently, because that makes easier to initiate large without being tracing back by authorities. It is utmost important the operators gain trust their customers blocking at edge network. To address this challenge, in paper, we present system called Caller-Centrality effectively...
IMS defines a generic architecture and framework that enables the convergence of voice, video, data mobile network technology over an IP-based infrastructure. The heterogeneity complexity will bring number challenges to integration products in mutli-vendor multi-protocol environment. Faults large, multi-technology complex are unavoidable, but quick detection identification can significantly improve reliability ensure robustness. Fault localization is central aspect fault management, process...
Machine learning (ML) based Malware Detection Systems (MDS) are the potential target of Hackers. authors usually have no information regarding MDS's classifier and its parameters. Therefore, such closed MDSs system exposed to blind black-box attacks can easily be bypassed with adversarial payloads. This vulnerability has attracted focus scholars. However, in existing research, payloads used for generated using static gradient approaches dynamic features (e.g., API calls) Portable Executables...
Summary Malware is a malicious program used for unauthorized access to organizational infrastructure and systems. To overcome challenges of exponential growth malware, notable research has been made unsupervised clustering Windows‐based portable executable (PE). Nevertheless, the best our knowledge there no robust cluster prediction Windows based PEs using static features. this end, we proposed an ensemble neural network architecture feature learning its distribution modeling PE(s). The...
Summary The uncontrollable spread of contagious disease COVID‐19 is a perennial threat to mankind and has resulted in an unprecedented lockdowns several countries including Pakistan which turn caused adverse socio‐economic impact all industries. strategic leadership concerned state authorities are trying hard combat control the pandemic. effective use Information Management & Decision Support (IMDS) System can play significant role combating pandemic its spread, managing relief actions...
Smartphones and tablets have become part of our daily lives. These devices run on two major competing software platforms: Apple's iOS the Google's Android OS. The popular design has implemented applications which are purchased by end users. apps mostly through Google Play Store, while available App Store. exclusively given birth to a new market as well, attracting all kinds interested users, hackers cybercriminals. In this paper, we focus being more susceptible attacks purchase or download...
Cyber-attacks have been menacing many organizations for a long time. With the advancement in technical growth, cyber-attacks also increased volume and treacherousness. For better detection of malware, model training over significant features is prime importance. In this study, we propose contrasting feature vectors clustering using multiple dimensionality reduction techniques such as PCA autoencoder. Three different models (HFVC, OEL, BENN) are proposed comprising architectures. To evaluate...