KRKongara Srinivasa Rao

Kongara Srinivasa Rao

*This is an algorithmically generated author record based on publicly available information.

Kongara Srinivasa Rao has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Interpretable-Aware Privacy Preserving Framework for Deepfake Detection using Federated ResNet and Explainable AI Techniques

    by Pochampally Chandra Sekhar Reddy, Kongara Srinivasa Rao

    The deepfake has grown faster with generative artificial intelligence which has made it much easier to produce realistic manipulated images and videos. These synthetic media raise serious concerns about the trustworthiness of information, digital security, personal privacy, and overall societal confidence. Traditional methods for detecting deepfakes depend on centralized deep learning systems that need to gather large amounts of images on a single server. To overcome the traditional challenges, this work introduces a new deepfake detection system designed to protect privacy by combining Federated Learning (FL) with Deep Learning (DL) and forensic analysis techniques. The system uses FL, which allows models to train on data stored locally across many devices without transferring the raw images anywhere. It’s built on the ResNet-18 architecture, chosen because it balances good detection capabilities with reasonable computational requirements. ResNet-18 residual learning helps the model train steadily and extract useful features, which fits well with the varied and distributed data environments in federated settings. Experiments are conducted using the FaceForensics++ dataset, a standard resource in media forensics studies which cover four types of manipulations DeepFakes, Face2Face, FaceSwap, and Neural Textures. Since client data distributions differ, which can slow down or destabilize federated training, the FedProx algorithm is used. FedProx adds a term to the local loss function to keep client model updates close to the global model, which helps reduce divergence between clients and improves overall training stability. After local training, only the updated model weights are sent to a central server, where they are averaged to create an improved global model. The experimental results show that the accuracy of 97.20%, precision 96.30%, recall of 96.72, f1-score of 96.90% to keep track of how well the model is learning and generalizing. This study demonstrates a unified framework integrating FL, CNNs, and explainability to enable secure, privacy-preserving, and interpretable deepfake detection, enhancing transparency and user trust.

  • Open Access

    Federated Deep Learning for Multi-Class Deepfake Detection Across Diverse Manipulations

    by Pochampally Chandra Sekhar Reddy, Kongara Srinivasa Rao

    The exponential growth of digital media, particularly through social networks generating approximately 0.5 zettabytes of data daily, has created unprecedented challenges in content authenticity verification. Advanced generative technologies including GANs, diffusion models, and transformers have enabled the creation of increasingly sophisticated deepfakes that manipulate facial features, attributes, and textures in images and videos. While numerous approaches utilizing deep learning architectures have been proposed for deepfake detection, current solutions often address specific manipulation types or datasets rather than offering comprehensive, generalizable frameworks. This research aims to develop a novel federated deep learning framework for multi-class deepfake detection that operates efficiently across diverse manipulation techniques and deployment scenarios. By leveraging transfer learning, temporal analysis, and privacy-preserving distributed computation, this work addresses critical gaps in deepfake detection research while providing practical solutions for real-world implementation.

  • Graph Neural Networks Unveiled: A Deep Dive into Models and Methods

    by K. Adi Narayana Reddy, M. Thukaram Reddy, Kongara Srinivasa Rao, E. Gurumohan Rao, B. Seetharamulu


  • Open Access

    Phishing website detection using novel integration of BERT and XLNet with deep learning sequential models

    by Kongara Srinivasa Rao, Dinesh Valluru, Satishkumar Patnala, Ravi Babu Devareddi, Tummalapalli Siva Rama Krishna, Andavarapu Sravani

    Phishing websites pose a significant threat to online security, necessitating robust detection mechanisms to safeguard users' sensitive information. This study explores the efficacy of various deep learning architectures for phishing website detection. Initially, traditional sequential models, including recurrent neural networks (RNN), long short-term memory (LSTM), and gated recurrent unit (GRU), achieve accuracies of 95%, 96%, and 96.5%, respectively, on a curated dataset. Building upon these results, hybrid architectures that combine the strengths of traditional sequential models with state-of-the-art language representation models, bidirectional encoder representations from transformers (BERT) and XLNet, are investigated. Combinations such as RNN with BERT, BERT with LSTM, BERT with GRU, RNN with XLNet, XLNet with LSTM, and XLNet with GRU are evaluated. Through experimentation, accuracies of 94.5%, 96.5%, 96.1%, 95.7%, 97.4%, and 97%, respectively, are achieved, demonstrating the effectiveness of hybrid deep learning architectures in enhancing phishing detection performance. These findings contribute to advancing the state-of-the-art in cybersecurity practices and underscore the importance of leveraging diverse model types to combat online threats effectively.


  • Advancements and Challenges in Text Summarization: An Overview of Methods and Strategies in Brief

    by Madhulika Yarlagadda, Hanumantha Rao Nadendla, Kongara Srinivasa Rao

  • An Automatic Text Summarization Method with the Concern of Covering Complete Formation

    by Srinivasa Rao Kongara, Dasika Sree Rama Chandra Murthy, Gangadhara Rao Kancherla

    Background: Text summarization is the process of generating a short description of the entire document which is more difficult to read. This method provides a convenient way of extracting the most useful information and a short summary of the documents. In the existing research work, this is focused by introducing the Fuzzy Rule-based Automated Summarization Method (FRASM). Existing work tends to have various limitations which might limit its applicability to the various real-world applications. The existing method is only suitable for the single document summarization where various applications such as research industries tend to summarize information from multiple documents. Methods: This paper proposed Multi-document Automated Summarization Method (MDASM) to introduce the summarization framework which would result in the accurate summarized outcome from the multiple documents. In this work, multi-document summarization is performed whereas in the existing system only single document summarization was performed. Initially document clustering is performed using modified k means cluster algorithm to group the similar kind of documents that provides the same meaning. This is identified by measuring the frequent term measurement. After clustering, pre-processing is performed by introducing the Hybrid TF-IDF and Singular value decomposition technique which would eliminate the irrelevant content and would result in the required content. Then sentence measurement is one by introducing the additional metrics namely Title measurement in addition to the existing work metrics to accurately retrieve the sentences with more similarity. Finally, a fuzzy rule system is applied to perform text summarization. Results: The overall evaluation of the research work is conducted in the MatLab simulation environment from which it is proved that the proposed research method ensures the optimal outcome than the existing research method in terms of accurate summarization. MDASM produces 89.28% increased accuracy, 89.28% increased precision, 89.36% increased recall value and 70% increased the f-measure value which performs better than FRASM. Conclusion: The summarization processes carried out in this work provides the accurate summarized outcome.


  • Semantic Similarity Based Automatic Document Summarization Method

    by K Sriniva Sa Rao, D S R Murthy, Gangadhara Rao Kancherla, Dept. Of Cse Professor

    Document summarization is the process of generating the summary of the documents gathered from the web sources. It reduces the burden of web readers by reducing the necessity of reading the entire document contents by generating the short summary. In our previous research work this is performed by introducing the method namely Noun weight based Automated Multi-Document Summarization method (NW-AMDSM). However the previous research work doesn’t concentrate on the semantic similarity which might reduce the accuracy of the summarization outcome. This is resolved in the proposed research method by introducing the method namely Semantic Similarity based Automatic Document Summarization Method (SS-ADSM). In this research work, multi document grouping is done is based on semantic similarity computation, thus the document with similar contents can be grouped more accurately. Here the semantic similarity computation is performed with the help of word net analyzer. The document grouping is done by introducing the modified FCM clustering algorithm. Finally hybrid neuro fuzzy genetic algorithm is introduced to perform the automatic summarization. The numerical analysis of the proposed research method is conducted in the matlab simulation environment and compared with other research methods in terms various performance metrics. The simulation analysis proved proposed method tends to have better performance in terms of increased accuracy of document summarization outcome.