Department of Computer Science and Information Systems

Permanent URI for this collectionhttp://localhost:4000/handle/123456789/1928

Browse

Subject: search.filters.subject.EEE

Search Results

Now showing 1 - 10 of 23
  • No Thumbnail Available
    Item
    An efficient federated transfer learning approach for Multi-UAV systems
    (IEEE, 2025-05) Joshi, Sandeep; Rajya Lakshmi, L.
    Recent advances in multi-unmanned aerial vehicle (UAV) based federated learning do not take into consideration the massive computational requirements of modern deep learning models on mobile UAV s. Additionally, there has been significant progress that shows that the information transmitted between the federated agent and the central hub can be attacked to undermine the privacy of the data. We propose a novel multi-UAV-based federated transfer learning system that drastically reduces the computational burden overall, shifts it from UAV s to the ground fusion center, and reduces the bandwidth requirements while enhancing its secure nature. The proposed system makes multi-UAV learning significantly fast, reliable, power efficient, and practically feasible. Furthermore, we provide simulation and experimental results to demonstrate the effectiveness of the proposed system
  • No Thumbnail Available
    Item
    Transformers for vision: a survey on innovative methods for computer vision
    (IEEE, 2025-05) Kumar, Dhruv; Chalapathi, G.S.S.
    Transformers have emerged as a groundbreaking architecture in the field of computer vision, offering a compelling alternative to traditional convolutional neural networks (CNNs) by enabling the modeling of long-range dependencies and global context through self-attention mechanisms. Originally developed for natural language processing, transformers have now been successfully adapted for a wide range of vision tasks, leading to significant improvements in performance and generalization. This survey provides a comprehensive overview of the fundamental principles of transformer architectures, highlighting the core mechanisms such as self-attention, multi-head attention, and positional encoding that distinguish them from CNNs. We delve into the theoretical adaptations required to apply transformers to visual data, including image tokenization and the integration of positional embeddings. A detailed analysis of key transformer-based vision architectures such as ViT, DeiT, Swin Transformer, PVT, Twins, and CrossViT are presented, alongside their practical applications in image classification, object detection, video understanding, medical imaging, and cross-modal tasks. The paper further compares the performance of vision transformers with CNNs, examining their respective strengths, limitations, and the emergence of hybrid models. Finally, current challenges in deploying ViTs, such as computational cost, data efficiency, and interpretability, and explore recent advancements and future research directions including efficient architectures, self-supervised learning, and multimodal integration are discussed.
  • No Thumbnail Available
    Item
    PUF-AQKD: a hardware-assisted quantum key distribution protocol for man-in-the-middle attack mitigation pdf
    (IEEE, 2025-05) Bhatia, Ashutosh; Bitragunta, Sainath; Tiwari, Kamlesh
    The Quantum Key Distribution (QKD) protocol utilizes quantum mechanics principles for cryptographic key exchange, ensuring absolute secrecy. Current QKD techniques are susceptible to man-in-the-middle (MITM) attacks due to the absence of an inherent mechanism for identity verification within the quantum channel. For authentication, these systems rely on classical or post-quantum cryptography, which diminishes the perfect security advantage provided by QKD. We present a Physical Unclonable Function (PUF)-based authenticated QKD protocol (PUF-AQKD), which avoids the necessity for authenticated classical channels and is useful in mitigating MITM attacks. The fundamental concept of PUF-AQKD is to implement a phase shift in the basis used for polarizing the transmitted qubits. The phase shift is dictated by PUFs, which are anticipated to result in analogous (correlated) responses for devices manufactured under similar conditions but dissimilar responses in different conditions. An adversary lacking a correlated PUF response shared by Alice and Bob would inadvertently increase the Quantum Bit Error Rates (QBER) observed at Bob’s end. We present a mathematical model to assess the efficacy of the proposed PUF-AQKD method and perform simulations utilizing the NetSquid simulator. The mathematical analysis and simulation findings indicate that PUF-AQKD can efficiently identify eavesdroppers, even during incomplete measurements, without the necessity of an authorized classical channel.
  • No Thumbnail Available
    Item
    Adaptive RIS design and optimization for cooperative ris-assisted wireless systems
    (IEEE, 2025-07) Bitragunta, Sainath; Bhatia, Ashutosh
    We propose an adaptive RIS-based cooperative transmission strategy that jointly selects one of two RIS paths and dynamically optimizes the number of active meta-atoms to maximize physical layer (PHY) secrecy capacity under a total average power constraint. Unlike existing approaches that fix the RIS size K or assume identical fading on all links, our framework uses long-term statistics to probabilistically choose between two RISs (upper or lower) with arbitrary first-hop fading, and leverages instantaneous channel state information (CSI) on the selected path to solve a convex K-sizing problem via a Lagrangian multiplier approach. We derive and present the solution for optimal K, and numerically evaluate the average PHY secrecy capacity and average PHY secrecy efficiency for the proposed optimal strategy. Numerical results show that the proposed optimal-K strategy achieves up to 35% higher average PHY secrecy capacity and 50% improvement in average PHY secrecy efficiency compared to a fixed-K benchmark strategy across moderate power thresholds. Furthermore, we present an insightful asymptotic analysis for average PHY secrecy capacity in an interesting scaling regime. Our findings demonstrate the practical benefits of adaptive RIS for cooperative PHY secure and energy-efficient beyond fifth generation (B5G) wireless systems
  • No Thumbnail Available
    Item
    Quantum key distribution optimization: reducing communication overhead in post-processing steps
    (IEEE, 2025-03) Bhatia, Ashutosh; Bitragunta, Sainath; Tiwari, Kamlesh
    Quantum Key Distribution (QKD) is a ground-breaking method in modern cryptography that uses quantum mechanics to establish secure communication channels. Unlike classical cryptographic techniques, QKD provides unconditional security based on quantum principles, such as the no-cloning theorem and the uncertainty principle. However, existing QKD systems often suffer from high overhead in key post-processing, affecting efficiency and scalability, especially in resource-constrained environments such as IoT. This paper addresses these challenges by introducing two key optimizations to enhance the efficiency and security of QKD systems. First, we propose a method using Pseudorandom Number Generators (PRNGs) to determine key bit positions for verification by Alice and Bob, significantly reducing communication over-head. Second, we employ hash-based subsequence comparison to minimize data exchange and leverage the cryptographic strength of hash functions. Results demonstrate that these strategies effectively reduce key post-processing overhead and improve the efficiency of QKD systems in real-world conditions making QKD more practical and scalable for diverse application contexts.
  • No Thumbnail Available
    Item
    Efficient routing for QKD network using novel quantum optimization approach
    (IEEE, 2025) Bitragunta, Sainath; Bhatia, Ashuthosh
    With exponential growth and associated milestones set in quantum information and quantum computing (QC) technologies, QC is becoming a threat to existing key encryption strategies that leverage asymmetric cryptographic algorithms like RSA (Rivest, Shamir, Adleman) encryption. Since these algorithms form the backbone of Internet communication, it becomes essential to utilize secure quantum methods for key generation and distribution. The quantum key distribution (QKD) networks have since been extensively researched and implemented with various communication protocols, primarily utilizing the Quantum Entanglement and Quantum Key Correction paradigms. Efficient routing is one of the significant problems in classical and hybrid networks. It is important to propose novel hybrid and efficient routing protocols based on modern optimization approaches to design secure, fidelitous, and efficient quantum information networks. We perform this optimization by generating a cost function to implement quantum optimization algorithms, namely the Quantum Approximate Optimization Algorithm (QAOA). We further draw a comparison with the state-of-the-art graph theory-based optimization techniques. The primary objective of this paper is to fabricate a robust quantum communication network and to subsequently analyze the effectiveness of quantum based techniques to carry out network routing and link optimization, generating scope for the utilization of quantum architecture to enhance security in Q KD networks.
  • No Thumbnail Available
    Item
    Enhanced lightweight quantum key distribution protocol for improved efficiency and security
    (IEEE, 2025) Bhatia, Ashutosh; Bitragunta, Sainath; Tiwari, Kamlesh
    Quantum Key Distribution (QKD) provides secure communication by leveraging quantum mechanics, with the BB84 protocol being one of its most widely adopted implementations. However, the classical post-processing steps in BB84, such as sifting, error correction, and key verification, often result in significant communication overhead, limiting its efficiency and scalability. In this work, we propose three key optimizations for BB84: (1) PRNG-based predetermined key bit positioning, which eliminates redundant bit exchanges during sifting, (2) hash-based subsequence comparison, enabling lightweight and efficient key verification, and (3) adaptive basis reconciliation, which minimizes the communication costs associated with basis matching. The proposed optimizations achieve a 50% reduction in communication overhead for large key sizes compared to traditional QKD protocols, as demonstrated through rigorous performance analysis. While the focus of this work is on the BB84 protocol, these optimizations are also directly applicable to a broader class of Discrete-Variable QKD (DV-QKD) protocols, such as six-state, B92, and E91, which share a fundamentally similar post-processing structure. This generality highlights the modularity and adaptability of the proposed methods across diverse QKD implementations. The proposed optimizations enhance post-processing efficiency and scalability, enabling practical deployment in bandwidth-limited environments like IoT networks, secure financial systems, and defense communications, thereby supporting broader adoption of quantum communication systems.
  • No Thumbnail Available
    Item
    Secrecy capacity and efficiency outage analysis of cooperative phy-secure wireless systems and secrecy capacity-based RIS design
    (IEEE, 2025-03) Bitragunta, Sainath; Bhatia, Ashutosh
    Physical layer (PHY) security (PLS) leverages the inherent randomness of wireless fading channels to provide enhanced secrecy capacity. In this work, we consider a four-node, dual hop, eavesdropper-aware cooperative PHY-security model. Considering probabilistic relay selection and relaying in the presence of hybrid fading channels, we develop an insightful analysis for the probability of PHY-secrecy capacity outage (PSCO) and PHY-secrecy efficiency outage (PSEO). Specifically, we derive closed form expressions for these performance measures and evaluate them numerically to obtain valuable qualitative insights. We also develop an insightful comparative study to show that the cooperative PLS relay model having a destination node equipped with multiple antennas and performing selection combining delivers superior PHY-secrecy outage performance. We extend the analysis to the reconfigurable intelligent surface (RIS)-assisted cooperative PLS system. Specifically, we address the design problem of N, the number of reflecting elements in RIS. We develop insightful criteria based on secrecy capacity to derive a closed form lower bound on N. This insightful result provides the values of N that could achieve superior PHY-secrecy capacity than the relay-assisted cooperative PLS system. Our analysis of the former cooperative PLS model and its extension to RIS design is useful for next generation cooperative PLS relay and RIS-assisted wireless systems and networks.
  • No Thumbnail Available
    Item
    Fuzzy Logic and AI-Powered, SDR Relay for Secure and Efficient Cooperative Radio Communication
    (IEEE, 2024) Bitragunta, Sainath; Bhatia, Ashuthosh
    In this article, we develop a novel approach that leverages the capabilities of fuzzy logic and artificial intelligence (AI) to develop an intelligent, efficient cooperative RCN. Software defined radio (SDR) is flexible, scalable, and reconfigurable. Considering heterogeneous radio communication networks (RCNs), conventional relays do not perform well due to their limitations (security vulnerabilities in cooperative Internet-of-Things (IoT), inefficiencies in half-duplex relaying, etc.). We propose an AI-powered, fuzzy logic-based SDR relay to address these issues. These intelligent relays could be useful and outperform conventional relays due to their adaptability and reconfigurabilty, with added intelligence based on AI and fuzzy logic. The proposed next generation SDR relays offer significant advantages over traditional relays and have the potential to revolutionize the field of radio communication. Specifically, we analyze the decimation technique in SDR signal-to-interference plus noise ratio (SINR) resampler, Mamdani fuzzy logic controller, and use a machine learning (ML) model that uses RADIOML data set. Based on the simulation results, we show that applying fuzzy logic with an ML-enabled SDR relay could improve energy efficiency and reliability performance in advanced radio networks.
  • No Thumbnail Available
    Item
    Experimental Analysis and Optimal Control of PZT Based Cantilever Beam Using Fuzzy-PID Controllers
    (IEEE, 2022) Yenuganti, Sujan
    In this study experimental analysis and control of a PZT based cantilever is performed using Fuzzy-PID controllers. Two PZT patches were attached to the rigid end of the Cantilever beam out of which one was used as an actuator and another PZT was used as a sensor. The sensor input was provided to a computer using an NI DAQ card. The sensor signal was received by the computer through LABVIEW software where the control algorithms using PID and Fuzzy-PID controller were designed. At the rigid end of the cantilever beam, a magnet was attached and an electromagnet was used as a controller for controlling the vibrations. The vibration suppression was done at the first order mode frequency of the cantilever beam and both PID and fuzzy-PID controllers show good suppression of the vibrations. However, the results show that fuzzy-PID controllers have better characteristics than PID control.