Browse
Recent Submissions
Item A NOVEL ENCRYPTION SCHEME BASED ON A KEY DEPENDENT SUBSTITUTION BOX(UMT, Lahore, 2024) SANAN AHMADData is the most crucial asset for any business to operate seamlessly. Organizations, enterprises, and individuals tend to share their private data daily over the insecure networks. Cryptosystems are employed to demonstrate the security of private communication and information networks. A cipher in cryptography is a set of predetermined procedures that may be used as a technique to achieve encryption and decryption. Various permutation and substitution techniques are employed for this purpose. S-Box oversees the substitution procedure. Modern ciphers employ dynamic, key-dependent S-Box. In this research effort, we suggested a way for creating dynamic S-Boxes with robust cryptographic features. Established benchmarks, such as bijectivity, nonlinearity, strict avalanche criteria, and linear probability, are utilized to evaluate the strength of the S-Box. After the creation of a dynamic S-Box, it is utilized in a novel cipher designed in this research effort. Novel cipher consists of three phases such as key generation, encryption, and decryption. A different S-Box is generated using values taken from the key and employed in a cipher round to make things more difficult for the attackers.Item A Novel Deep Architecture Based On LSTM And XGBoost For Movie Revenue Prediction(UMT, Lahore, 2024) Muhammad YasirMovie revenue is a crucial determinant of a film’s success and profitability in the highly competitive entertainment industry. Due to the unpredictability of the entertainment industry, predicting movie revenue is a difficult task. By examining different variables that affect revenue, Deep learning algorithms deliver highly reliable revenue estimates by analyzing multiple variables: genre, cast, budget, release date, marketing techniques, and viewer demographics. A precise revenue forecast can aid studios in maximizing their marketing initiatives, lowering financial risks, and boosting profitability. Previous studies on predicting movie revenue are the complex and unpredictable nature of factors that influence box office performance, which has led to a lack of accuracy in previous studies. In this study, we propose a feature-based approach using a hybrid approach of Xg Boost and LSTM network for predicting movie revenue, achieving a remarkable 99% accuracy with the Movie dataset and achieving a Mean Square Error (MSE) of 0.002 represents a significant improvement compared to previous research where MSE and accuracy values were above the State of the art. Also, the highest F1 score 87% demonstrates the superior accuracy and predictive capability of our model. Our approach utilizes the dataset that contains 75k rows this is a huge data to predict movie revenue. This advanced modification significantly enhances predictive performance, making our model highly effective in forecasting movie revenue The study also presents a comprehensive framework for the prediction of movie income, best practices, and methodological levels for creating revenue prediction models, contributing to the subject of computational prediction of film revenue Overall, this research highlights the effectiveness of deep learning techniques in forecasting movie revenue, providing valuable insights for stakeholders in the film industry.Item BLOCKCHAIN-BASED ARCHITECTURE FOR A RELIABLE AND TRANSPARENT POTATO SEED SUPPLY CHAIN(UMT, Lahore, 2024) ZAINAB KHALIDAgriculture production and growing demand for food around the globe have aroused concern related to food safety and a renewed focus on the quality of food in the supply chain. Due to growing contamination risks and increasing issues of food safety has developed an immense need for an effective traceability solution. The traditional systems have data tampering issues and low traceability efficiency in the current supply chain. Blockchain technology is a disruptive paradigm for the traceability of agricultural products in the food supply chain. In this study we have proposed a trusted, reliable, and transparent potato seed supply chain framework based on Blockchain technology. In order to record the transactions among stakeholders, a new crypto coin, Potato Seed Coin (PSC) is introduced. Furthermore, the developed framework consists of a crypto wallet, an economic model, and Initial Coin Offering (ICO). Besides, designed a transparent system to process real-time transactions by implementing smart contracts for the traceability of potato seed. Moreover, this study presents an Inter Planetary File System for farmers, retailers, companies, and all other stakeholders to store encrypted data with high data security and complete transparency. Lastly, research results show that the proposed framework has better performance in terms of new block latency, gas cost, and verification time of a transaction.Item A Novel Approach for Data Security Using a Logarithmic-Based Dynamic Substitution Box and its Application in a New Cipher(UMT, Lahore, 2024) AMNA RAMZANCryptography plays a crucial role in securing communication and data in modern information systems. Encryption is a common approach for data protection, and substitution boxes (S-box) are an essential component of many encryption schemes. Chaotic mapping is a promising method for producing S-box that improve the security of cryptographic algorithms because it exploits chaotic systems' intrinsic randomness to generate unpredictable patterns. In this thesis, we propose a novel approach for generating a dynamic and key-dependent S-Boxes using a chaotic map. Our method uses a distinctive chaotic map with a random distribution to build robust S-Boxes with high cryptographic strength. A new cipher is created by using a new function and the newly developed S-Box. Along with the decryption procedure, the key generation approach for the cipher is also described. The method is thoroughly tested to assure that it meets strict avalanche criterion, linear approximation probability, differential approximation probability, bit independent criterion, and nonlinearity analysis requirements. A comparison with current S-Boxes based on chaotic maps verifies that proposed S-Box which demonstrates optimum performance and durability against differential cryptanalysis.Item A Blockchain-Based Framework for Distributed Agile Software Testing Life Cycle(UMT, Lahore, 2024) Fatima AhmedA blockchain-based architecture optimizes the distributed agile software testing life cycle. Previously used communication and collaboration methods in software testing lacked trust, traceability, and security. Developers' failure to complete unit testing resulted in delayed testing, a major cause of project failure. This study explores how using blockchain technology in software testing addresses concerns about coordination, communication. trust and transparency. I suggested Testing Plus, a blockchain-based architecture. The Testing Plus framework uses blockchain to establish a transparent and secure platform for verification of payments and acceptance testing. Moreover, incomplete unit testing by developers contributed significantly to the project's failure by delaying testing. This paper discusses the blockchain technology integrating in software testing and addresses important issues with collaboration, interaction, transparency, and trust. We proposed Testing Plus, a blockchain-based platform. The Testing Plus offers a transparent and safe environment for acceptance testing and verification of payments by utilising blockchain technology. A private Ethereum blockchain network is used by TestingPlus. Private blockchain networks provide greater control and privacy compared to public ones. Implementing private Ethereum blockchain smart contracts, Testing Plus will verify that the development and the testing crew are both aim towards the same objective and receiving just compensation for their services