9th International Conference on ICT for Sustainable Development

Authors - Harsh Dudhat, Krunal Jodhani, Jyot Delvadiya, Utsav Gundaraniya, Sneha Padhiar, Raj Fachara
Abstract - Cryptography is the basis of modern information security, combining symmetric and asymmetric algorithms to protect digital information. This article presents a comparison of the main algorithms in the two fields. Explore symmetry algorithms such as RC4, AES and DES for their performance, security, and versatility. In contrast, asymmetric algorithms such as RSA, ECC and ElGamal are analyzed for their management complexity, computational overhead, and vulnerability to cryptographic attacks. Understanding the unique characteristics of each algorithm allows practitioners to make informed decisions about choosing the encryption method that best suits their specific security needs. This misunderstanding is necessary to create resilient cryptographic systems and reduce vulnerabilities in digital systems. In addition, this research contributes to cryptographic knowledge by addressing new trends and current issues in the field. The insights gained from this research not only help support the use of strong encryption techniques but also lay the foundation for future innovations in digital security techniques. Finally, this article aims to deepen the understanding of the encryption process so that participants can investigate complex problems and create secure system knowledge. It aims to increase the effectiveness of digital systems against changing threats in the connected world through comprehensive analysis and to ensure the integrity and confidentiality of sensitive data.

Authors - Aashka Raval, Jaivik Jariwala, Vrundan Sojitra, Nishant Doshi
Abstract - Encryption and decryption are used even before the word democracy came into existence. Asset encryption systems rely on key sharing (public or private) between peers involved in exchanging encrypted messages, but with the passage of time, we have observed concerns towards privacy. Users or key service providers have exclusive rights to data and when we talk about the cloud is known how vulnerable our data is to cloud providers as well as third-party service providers. Even if the keys are not shared, encrypted equipment is shared with someone who does not need access to the content, and all this access is provided through untrusted sources like computers, servers to all the accessible places and people they do not even need permission which makes it freer to violate privacy. Indeed, Homomorphic Encryption (HE), a special type of encryption system, can address this concern as it allows any outside organization to process encrypted data without having to extract it prematurely. Although this extremely useful feature of the HE system has been known for more than 30 years, the first sound and accessible Fully Homomorphic Encryption (FHE) system, which allows any tangible work to be done on encrypted data, was introduced by Craig Gentry in 2009. While this has been a remarkable success, the different uses have so far shown that FHE still needs significant improvements to work across all platforms. This paper focuses on the comparison of Partially Homomorphic Encryption (PHE) and Fully Homomorphic Encryption in cloud computing. Both have some pros and cons and the computation is a crucial part of the implementation to see how they work.

Authors - Samarth Ashok Pujari, Shubham Anil Taru, Nikita Arjun Bhutnale, Manav Ashok Thakur, Sthavir Mahendra Rokade
Abstract - The Attendance Portal is software designed to effectively manage student attendance on a daily basis within a school environment. This system is responsible for maintaining detailed records of student attendance, generating reports based on their presence in class, and providing access to both staff and students through individualized usernames and passwords. Staff members are granted separate credentials to mark students' attendance, ensuring accountability and accuracy in attendance tracking. Each staff member is assigned a unique username and password for attendance management purposes. This system generates precise reports reflecting student attendance on a weekly and monthly basis, facilitating comprehensive oversight of attendance patterns. Furthermore, students are provided with their own login credentials, allowing them to access and review their attendance status independently. This enhances transparency and encourages students to actively monitor their attendance records. The UNIXCOLL Attendance Management System prioritizes data accuracy, security, and accessibility, ensuring a streamlined and efficient process for monitoring and managing student attendance within the educational setting.

Authors - Rushikesh Joshi, Vijay Shilwant, Roshan Dandge, Shreyash Rajput, Manav Ashok Thakur
Abstract - We have designed a campus placement prediction system aimed at assessing a student's likelihood of securing employment through campus recruitment. This predictive model incorporates multiple parameters to gauge a student's skill level. Some of these parameters are drawn from the college's records, including academic performance, CGPA, attendance, and more, while others are derived from assessments conducted within the placement management system. By amalgamating these data points, our model can provide accurate predictions regarding a student's potential placement in a company. Furthermore, we leverage data from previous group of students to train our model, employing educational data mining techniques to access authentic historical data from our college's alumni. This approach enhances the efficacy of our machine learning model when making predictions specific to our institution.

Authors - Pranav Palkar, Sumit Nevase, Makarand Goralkar, Aditya Patil, Rashmi S. Bhumbare
Abstract - Site makes it straightforward to connected with client with simple get to to all substance. The current site of our college is overseen by a company, so there are few disadvantages. As the college need to pay huge sum and there was too chance of information misfortune so to overcome this issue we have created “VPSCET” college site. In our site we have utilized MySQL and PHP as backend plan and HTML, CSS and JavaScript are utilized as front conclusion apparatuses. The most point of our extend is to alter substance powerfully and to supply utilize interface applications. This location will give virtual visit of campus, here we are going get most recent subtle elements approximately the institution VPS/edu.Com was a web plan extend attempted on sake of five offices and an regulatory office of the College of Vidhya Prasarini Sabha's college Of Building and Innovation. The part of the VPS/edu.Com center group was to supply plan and specialized direction for the our group working straightforwardly with these units. The center group made a model from which the unit groups planned their person destinations. Afterward the center group made a difference actualize the unit destinations. As portion of the plan exertion, the center group inspected various college Web destinations and thought through a assortment of plan issues. Three are talked about in this paper: (1) showing the personality of person units inside the various leveled structure of the institution. (2) keeping up visual consistency all through the location (3) harmonizing the messages passed on by the university's domestic page and the domestic pages of the university's colleges and division.

Authors - Rashmi S Bhumbare, Aarti Machhindra Chavan, Mayuri Sanjay Chavan, Pratiksha Vijay Chavan, Shejal Sanjay Pawar
Abstract - In contemporary times, video surveillance assumes a crucial role, especially given the widespread adoption of cutting-edge technologies such as artificial intelligence, machine learning, and deep learning. These advancements have fostered the creation of intricate systems capable of discerning various forms of questionable conduct from live video streams. Identifying suspicious behavior, often subtle and challenging to discern from typical actions, proves to be one of the most demanding tasks. To tackle this hurdle, a blend of methodologies, including deep learning, is utilized. Deep learning algorithms are trained to identify anomalous patterns of behavior across diverse settings, notably within educational institutions. The surveillance process typically encompasses the examination of frames extracted from video recordings. These frames undergo a dual-stage processing: initial feature extraction followed by classification using these features to ascertain the presence of suspicious behavior. In essence, these dynamic systems harness state-of-the-art technology to bolster surveillance capabilities, facilitating prompt identification and response to potential security risks. Upon detecting suspicious activities, timely alert notifications are dispatched to relevant authorities, ensuring a proactive stance towards upholding safety and security.

Authors - Pratik Haribhakta, Shubham Raut, Bramhadev Garud, Priti Chorade
Abstract - This study focuses on the example of segregation of personal items in high-risk sectors such as clothing and personal protective equipment. We propose using biometric objects from Open Images V5 and DeepFashion2 datasets for pre-training mask segmentation networks for recognition and segmentation of personal protective equipment in the workplace. The preliminary results of our proposed model achieve a mean average precision with modest optimization, which results in extremely effective segmentation of welding masks, high visibility vests, construction helmets, and ear protection in the workplace. The results of this research can be applied to improve workplace safety in high-risk industries by providing a way to ensure that personal protective equipment (PPE) is used appropriately while protecting employee privacy.