Vivek Chaturvedi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Vivek Chaturvedi has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Muhammad Shafique
New York University Abu Dhabi (NYUAD)
10 shared publications Gang Quan
Florida International University, Miami, FL, USA
9 shared publicationsThambipillai Srikanthan
School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore
7 shared publications- Wei Zhang
The Hong Kong University of Science and Technology
6 shared publications Vijeta Rathore
School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore
5 shared publicationsYingnan Cui
Nanyang Technological University, N4-02a-32 Nanyang Avenue, Singapore
4 shared publications
Latest Publications
- 29 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (14) , 31229-31239
ViT-EBoT: Vision Transformer for Encrypted Botnet Detection in Resource-Constrained Edge Devices
With the advent of lightweight cryptography in edge devices, attackers can hide malicious code under encrypted network communications to perform malware attacks. This makes IoT botnet attacks extremely challenging to detect using traditional signature-based techniques. In this paper, we propose a novel IoT botnet detection framework that uses vision transformers to detect malicious communications captured in encrypted network flow images. Our approach achieved ∼98% accuracy and around 94% reduced inference latency compared to network flow header analysis, the popular network-based botnet detection technique. Further, we have validated the practicality of our approach by testing it on Jetson Orin Nano acting as an edge gateway and achieved reduced inference latency of 25.16 ms and area overhead of 88.13 MB.
- 29 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (14) , 31229-31239
ViT-EBoT: Vision Transformer for Encrypted Botnet Detection in Resource-Constrained Edge Devices
With the advent of lightweight cryptography in edge devices, attackers can hide malicious code under encrypted network communications to perform malware attacks. This makes IoT botnet attacks extremely challenging to detect using traditional signature-based techniques. In this paper, we propose a novel IoT botnet detection framework that uses vision transformers to detect malicious communications captured in encrypted network flow images. Our approach achieved ∼98% accuracy and around 94% reduced inference latency compared to network flow header analysis, the popular network-based botnet detection technique. Further, we have validated the practicality of our approach by testing it on Jetson Orin Nano acting as an edge gateway and achieved reduced inference latency of 25.16 ms and area overhead of 88.13 MB.
- 12 February 2026
- Published by Springer Nature
- p. 298-317
VulScan-LT: A Lightweight Transformer-Based Software Vulnerability Scanning Tool for Resource-Constrained Edge Devices
- 12 February 2026
- Published by Springer Nature
- p. 298-317
VulScan-LT: A Lightweight Transformer-Based Software Vulnerability Scanning Tool for Resource-Constrained Edge Devices
- Open Access
CapsBeam: Accelerating Capsule Network based Beamformer for Ultrasound Non-Steered Plane Wave Imaging on Field Programmable Gate Array
In recent years, there has been a growing trend in accelerating computationally complex non-real-time beamforming algorithms in ultrasound imaging using deep learning models. However, due to the large size and complexity these state-of-the-art deep learning techniques poses significant challenges when deploying on resource-constrained edge devices. In this work, we propose a novel capsule network based beamformer called CapsBeam, designed to operate on raw radio-frequency data and provide an envelope of beamformed data through non-steered plane wave insonification. Experiments on in-vivo data, CapsBeam reduced artifacts compared to the standard Delay-and-Sum (DAS) beamforming. For in-vitro data, CapsBeam demonstrated a 32.31% increase in contrast, along with gains of 16.54% and 6.7% in axial and lateral resolution compared to the DAS. Similarly, in-silico data showed a 26% enhancement in contrast, along with improvements of 13.6% and 21.5% in axial and lateral resolution, respectively, compared to the DAS. To reduce the parameter redundancy and enhance the computational efficiency, we pruned the model using our multi-layer LookAhead Kernel Pruning (LAKP-ML) methodology, achieving a compression ratio of 85% without affecting the image quality. Additionally, the hardware complexity of the proposed model is reduced by applying quantization, simplification of non-linear operations, and parallelizing operations. Finally, we proposed a specialized accelerator architecture for the pruned and optimized CapsBeam model, implemented on a Xilinx ZU7EV FPGA. The proposed accelerator achieved a throughput of 30 GOPS for the convolution operation and 17.4 GOPS for the dynamic routing operation.
Open AccessCapsBeam: Accelerating Capsule Network based Beamformer for Ultrasound Non-Steered Plane Wave Imaging on Field Programmable Gate Array
In recent years, there has been a growing trend in accelerating computationally complex non-real-time beamforming algorithms in ultrasound imaging using deep learning models. However, due to the large size and complexity these state-of-the-art deep learning techniques poses significant challenges when deploying on resource-constrained edge devices. In this work, we propose a novel capsule network based beamformer called CapsBeam, designed to operate on raw radio-frequency data and provide an envelope of beamformed data through non-steered plane wave insonification. Experiments on in-vivo data, CapsBeam reduced artifacts compared to the standard Delay-and-Sum (DAS) beamforming. For in-vitro data, CapsBeam demonstrated a 32.31% increase in contrast, along with gains of 16.54% and 6.7% in axial and lateral resolution compared to the DAS. Similarly, in-silico data showed a 26% enhancement in contrast, along with improvements of 13.6% and 21.5% in axial and lateral resolution, respectively, compared to the DAS. To reduce the parameter redundancy and enhance the computational efficiency, we pruned the model using our multi-layer LookAhead Kernel Pruning (LAKP-ML) methodology, achieving a compression ratio of 85% without affecting the image quality. Additionally, the hardware complexity of the proposed model is reduced by applying quantization, simplification of non-linear operations, and parallelizing operations. Finally, we proposed a specialized accelerator architecture for the pruned and optimized CapsBeam model, implemented on a Xilinx ZU7EV FPGA. The proposed accelerator achieved a throughput of 30 GOPS for the convolution operation and 17.4 GOPS for the dynamic routing operation.
- Open Access
FastCaps: A Design Methodology for Accelerating Capsule Network on Field Programmable Gate Arrays
Capsule Network (CapsNet) has shown significant improvement in understanding the variation in images along with better generalization ability compared to traditional Convolutional Neural Network (CNN). CapsNet preserves spatial relationship among extracted features and apply dynamic routing to efficiently learn the internal connections between capsules. However, due to the capsule structure and the complexity of the routing mechanism, it is non-trivial to accelerate CapsNet performance in its original form on Field Programmable Gate Array (FPGA). Most of the existing works on CapsNet have achieved limited acceleration as they implement only the dynamic routing algorithm on FPGA, while considering all the processing steps synergistically is important for real-world applications of Capsule Networks. Towards this, we propose a novel two-step approach that deploys a full-fledged CapsNet on FPGA. First, we prune the network using a novel Look-Ahead Kernel Pruning (LAKP) methodology that uses the sum of look-ahead scores of the model parameters. Next, we simplify the nonlinear operations, reorder loops, and parallelize operations of the routing algorithm to reduce CapsNet hardware complexity. To the best of our knowledge, this is the first work accelerating a full-fledged CapsNet on FPGA. Experimental results on the MNIST and F-MNIST datasets (typical in Capsule Network community) show that the proposed LAKP approach achieves an effective compression rate of 99.26% and 98.84%, and achieves a throughput of 82 FPS and 48 FPS on Xilinx PYNQ-Z1 FPGA, respectively. Furthermore, reducing the hardware complexity of the routing algorithm increases the throughput to 1351 FPS and 934 FPS respectively. As corroborated by our results, this work enables highly performance-efficient deployment of CapsNets on low-cost FPGA that are popular in modern edge devices.
Open AccessFastCaps: A Design Methodology for Accelerating Capsule Network on Field Programmable Gate Arrays
Capsule Network (CapsNet) has shown significant improvement in understanding the variation in images along with better generalization ability compared to traditional Convolutional Neural Network (CNN). CapsNet preserves spatial relationship among extracted features and apply dynamic routing to efficiently learn the internal connections between capsules. However, due to the capsule structure and the complexity of the routing mechanism, it is non-trivial to accelerate CapsNet performance in its original form on Field Programmable Gate Array (FPGA). Most of the existing works on CapsNet have achieved limited acceleration as they implement only the dynamic routing algorithm on FPGA, while considering all the processing steps synergistically is important for real-world applications of Capsule Networks. Towards this, we propose a novel two-step approach that deploys a full-fledged CapsNet on FPGA. First, we prune the network using a novel Look-Ahead Kernel Pruning (LAKP) methodology that uses the sum of look-ahead scores of the model parameters. Next, we simplify the nonlinear operations, reorder loops, and parallelize operations of the routing algorithm to reduce CapsNet hardware complexity. To the best of our knowledge, this is the first work accelerating a full-fledged CapsNet on FPGA. Experimental results on the MNIST and F-MNIST datasets (typical in Capsule Network community) show that the proposed LAKP approach achieves an effective compression rate of 99.26% and 98.84%, and achieves a throughput of 82 FPS and 48 FPS on Xilinx PYNQ-Z1 FPGA, respectively. Furthermore, reducing the hardware complexity of the routing algorithm increases the throughput to 1351 FPS and 934 FPS respectively. As corroborated by our results, this work enables highly performance-efficient deployment of CapsNets on low-cost FPGA that are popular in modern edge devices.
- Open Access
- 1 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. PP, 1
FeatuReBeam: Efficient Beamforming for High-Frame Ultrasound Imaging using Adaptive Feature Reuse with (m,k)-Guarantee
Existing tissue adaptive deep learning-based ultrasound image reconstruction models are computationally intensive, and achieving high frame rates particularly in the application of B-mode imaging on resource-constrained devices is challenging. Based on a traditional firm guarantee real-time model, i.e., the (m,k)-model, we propose a methodology that can take advantage of the similarity among feature maps generated by continuous frames to reduce the redundant computations and, thus, significantly improve the throughput and energy efficiency. A comprehensive evaluation on in-vitro and in-vivo data using U-Net and GoogLeNet-based beamformers demonstrated over a 50% reduction in computational complexity while preserving the original image quality. The implementation of the proposed methodology on the Xilinx ZU7EV FPGA achieved latency improvement of over 45% and 46% for the U-Net and GoogLeNet models, respectively. Additionally, when compared to state-of-the-art filter pruning approaches, including magnitude-based and feature map-based filter pruning, the proposed methodology outperformed both in terms of computational reduction and output image quality, achieving over a 14% improvement on the Xilinx ZU7EV FPGA.
- 1 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. PP, 1
Open AccessFeatuReBeam: Efficient Beamforming for High-Frame Ultrasound Imaging using Adaptive Feature Reuse with (m,k)-Guarantee
Existing tissue adaptive deep learning-based ultrasound image reconstruction models are computationally intensive, and achieving high frame rates particularly in the application of B-mode imaging on resource-constrained devices is challenging. Based on a traditional firm guarantee real-time model, i.e., the (m,k)-model, we propose a methodology that can take advantage of the similarity among feature maps generated by continuous frames to reduce the redundant computations and, thus, significantly improve the throughput and energy efficiency. A comprehensive evaluation on in-vitro and in-vivo data using U-Net and GoogLeNet-based beamformers demonstrated over a 50% reduction in computational complexity while preserving the original image quality. The implementation of the proposed methodology on the Xilinx ZU7EV FPGA achieved latency improvement of over 45% and 46% for the U-Net and GoogLeNet models, respectively. Additionally, when compared to state-of-the-art filter pruning approaches, including magnitude-based and feature map-based filter pruning, the proposed methodology outperformed both in terms of computational reduction and output image quality, achieving over a 14% improvement on the Xilinx ZU7EV FPGA.
- Open Access
- 25 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 52-63
Extracting Proxy Models from Side-Channel Insights to Enhance Adversarial Attacks on Black-Box DNNs
- 25 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 52-63
Open AccessExtracting Proxy Models from Side-Channel Insights to Enhance Adversarial Attacks on Black-Box DNNs
- 25 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 33 (7) , 1934-1944
CapsBeam: Accelerating Capsule Network-Based Beamformer for Ultrasound Nonsteered Plane-Wave Imaging on Field-Programmable Gate Array
In recent years, there has been a growing trend in accelerating computationally complex nonreal-time beamforming algorithms in ultrasound imaging using deep learning models. However, due to the large size and complexity, these state-of-the-art deep learning techniques pose significant challenges when deploying on resource-constrained edge devices. In this work, we propose a novel capsule network-based beamformer called CapsBeam, designed to operate on raw radio frequency data and provide an envelope of beamformed data through nonsteered plane-wave insonification. In experiments on in vivo data, CapsBeam reduced artifacts compared to the standard Delay-and-Sum (DAS) beamforming. For in vitro data, CapsBeam demonstrated a 32.31% increase in contrast, along with gains of 16.54% and 6.7% in axial and lateral resolution compared to the DAS. Similarly, in silico data showed a 26% enhancement in contrast, along with improvements of 13.6% and 21.5% in axial and lateral resolution, respectively, compared to the DAS. To reduce the parameter redundancy and enhance the computational efficiency, we pruned the model using our multilayer look-ahead kernel pruning (LAKP-ML) methodology, achieving a compression ratio of 85% without affecting the image quality. Additionally, the hardware complexity of the proposed model is reduced by applying quantization, simplification of nonlinear operations, and parallelizing operations. Finally, we proposed a specialized accelerator architecture for the pruned and optimized CapsBeam model, implemented on a Xilinx ZU7EV FPGA. The proposed accelerator achieved a throughput of 30 GOPS for the convolution operation and 17.4 GOPS for the dynamic routing operation.
- 25 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 33 (7) , 1934-1944
CapsBeam: Accelerating Capsule Network-Based Beamformer for Ultrasound Nonsteered Plane-Wave Imaging on Field-Programmable Gate Array
In recent years, there has been a growing trend in accelerating computationally complex nonreal-time beamforming algorithms in ultrasound imaging using deep learning models. However, due to the large size and complexity, these state-of-the-art deep learning techniques pose significant challenges when deploying on resource-constrained edge devices. In this work, we propose a novel capsule network-based beamformer called CapsBeam, designed to operate on raw radio frequency data and provide an envelope of beamformed data through nonsteered plane-wave insonification. In experiments on in vivo data, CapsBeam reduced artifacts compared to the standard Delay-and-Sum (DAS) beamforming. For in vitro data, CapsBeam demonstrated a 32.31% increase in contrast, along with gains of 16.54% and 6.7% in axial and lateral resolution compared to the DAS. Similarly, in silico data showed a 26% enhancement in contrast, along with improvements of 13.6% and 21.5% in axial and lateral resolution, respectively, compared to the DAS. To reduce the parameter redundancy and enhance the computational efficiency, we pruned the model using our multilayer look-ahead kernel pruning (LAKP-ML) methodology, achieving a compression ratio of 85% without affecting the image quality. Additionally, the hardware complexity of the proposed model is reduced by applying quantization, simplification of nonlinear operations, and parallelizing operations. Finally, we proposed a specialized accelerator architecture for the pruned and optimized CapsBeam model, implemented on a Xilinx ZU7EV FPGA. The proposed accelerator achieved a throughput of 30 GOPS for the convolution operation and 17.4 GOPS for the dynamic routing operation.
- Open Access
S-E Pipeline: A Vision Transformer (ViT) based Resilient Classification Pipeline for Medical Imaging Against Adversarial Attacks
Vision Transformer (ViT) is becoming widely popular in automating accurate disease diagnosis in medical imaging owing to its robust self-attention mechanism. However, ViTs remain vulnerable to adversarial attacks that may thwart the diagnosis process by leading it to intentional misclassification of critical disease. In this paper, we propose a novel image classification pipeline, namely, S-E Pipeline, that performs multiple pre-processing steps that allow ViT to be trained on critical features so as to reduce the impact of input perturbations by adversaries. Our method uses a combination of segmentation and image enhancement techniques such as Contrast Limited Adaptive Histogram Equalization (CLAHE), Unsharp Masking (UM), and High-Frequency Emphasis filtering (HFE) as preprocessing steps to identify critical features that remain intact even after adversarial perturbations. The experimental study demonstrates that our novel pipeline helps in reducing the effect of adversarial attacks by 72.22% for the ViT-b32 model and 86.58% for the ViT-l32 model. Furthermore, we have shown an end-to-end deployment of our proposed method on the NVIDIA Jetson Orin Nano board to demonstrate its practical use case in modern hand-held devices that are usually resource-constrained.
Open AccessS-E Pipeline: A Vision Transformer (ViT) based Resilient Classification Pipeline for Medical Imaging Against Adversarial Attacks
Vision Transformer (ViT) is becoming widely popular in automating accurate disease diagnosis in medical imaging owing to its robust self-attention mechanism. However, ViTs remain vulnerable to adversarial attacks that may thwart the diagnosis process by leading it to intentional misclassification of critical disease. In this paper, we propose a novel image classification pipeline, namely, S-E Pipeline, that performs multiple pre-processing steps that allow ViT to be trained on critical features so as to reduce the impact of input perturbations by adversaries. Our method uses a combination of segmentation and image enhancement techniques such as Contrast Limited Adaptive Histogram Equalization (CLAHE), Unsharp Masking (UM), and High-Frequency Emphasis filtering (HFE) as preprocessing steps to identify critical features that remain intact even after adversarial perturbations. The experimental study demonstrates that our novel pipeline helps in reducing the effect of adversarial attacks by 72.22% for the ViT-b32 model and 86.58% for the ViT-l32 model. Furthermore, we have shown an end-to-end deployment of our proposed method on the NVIDIA Jetson Orin Nano board to demonstrate its practical use case in modern hand-held devices that are usually resource-constrained.
- Open Access
- 9 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 26943-26956
FRNet: A Feature-Rich CNN Architecture to Defend Against Adversarial Attacks
Adversarial attacks that are possible in natural images are also transferable to medical images, paralyzing the diagnostic process and threatening the robustness of underlying Convolutional Neural Network (CNN) based classifiers. In this work, we have first demonstrated the effectiveness of well-known natural image adversarial attacks such as FGSM and PGD on Malaria cell images. Afterwards, we propose a novel defense methodology, namely FRNet, that leverages well-established features such as HOG, LBP, KAZE, and SIFT that are able to detect edges and objects while they remain robust against imperceptible adversarial perturbations. The method utilizes an MLP to efficiently concatenate the features to FRNet making it convenient and resulting in an architecturally neural and attack generic methodology. Our experimental results demonstrate that when applying FRNet on different CNN architectures such as simple CNN, EfficientNet, and MobileNet, it decreases the impact of adversarial attacks by as much as 67% compared to the corresponding base models.
- 9 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 26943-26956
Open AccessFRNet: A Feature-Rich CNN Architecture to Defend Against Adversarial Attacks
Adversarial attacks that are possible in natural images are also transferable to medical images, paralyzing the diagnostic process and threatening the robustness of underlying Convolutional Neural Network (CNN) based classifiers. In this work, we have first demonstrated the effectiveness of well-known natural image adversarial attacks such as FGSM and PGD on Malaria cell images. Afterwards, we propose a novel defense methodology, namely FRNet, that leverages well-established features such as HOG, LBP, KAZE, and SIFT that are able to detect edges and objects while they remain robust against imperceptible adversarial perturbations. The method utilizes an MLP to efficiently concatenate the features to FRNet making it convenient and resulting in an architecturally neural and attack generic methodology. Our experimental results demonstrate that when applying FRNet on different CNN architectures such as simple CNN, EfficientNet, and MobileNet, it decreases the impact of adversarial attacks by as much as 67% compared to the corresponding base models.
- Open Access
- 9 September 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 22 (5s) , 1-26
ViT4Mal: Lightweight Vision Transformer for Malware Detection on Edge Devices
There has been a tremendous growth of edge devices connected to the network in recent years. Although these devices make our life simpler and smarter, they need to perform computations under severe resource and energy constraints, while being vulnerable to malware attacks. Once compromised, these devices are further exploited as attack vectors targeting critical infrastructure. Most existing malware detection solutions are resource and compute-intensive and hence perform poorly in protecting edge devices. In this paper, we propose a novel approach ViT4Mal that utilizes a lightweight vision transformer (ViT) for malware detection on an edge device. ViT4Mal first converts executable byte-code into images to learn malware features and later uses a customized lightweight ViT to detect malware with high accuracy. We have performed extensive experiments to compare our model with state-of-the-art CNNs in the malware detection domain. Experimental results corroborate that ViTs don’t demand deeper networks to achieve comparable accuracy of around 97% corresponding to heavily structured CNN models. We have also performed hardware deployment of our proposed lightweight ViT4Mal model on the Xilinx PYNQ Z1 FPGA board by applying specialized hardware optimizations such as quantization, loop pipelining, and array partitioning. ViT4Mal achieved an accuracy of ~94% and a 41x speedup compared to the original ViT model.
- 9 September 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 22 (5s) , 1-26
Open AccessViT4Mal: Lightweight Vision Transformer for Malware Detection on Edge Devices
There has been a tremendous growth of edge devices connected to the network in recent years. Although these devices make our life simpler and smarter, they need to perform computations under severe resource and energy constraints, while being vulnerable to malware attacks. Once compromised, these devices are further exploited as attack vectors targeting critical infrastructure. Most existing malware detection solutions are resource and compute-intensive and hence perform poorly in protecting edge devices. In this paper, we propose a novel approach ViT4Mal that utilizes a lightweight vision transformer (ViT) for malware detection on an edge device. ViT4Mal first converts executable byte-code into images to learn malware features and later uses a customized lightweight ViT to detect malware with high accuracy. We have performed extensive experiments to compare our model with state-of-the-art CNNs in the malware detection domain. Experimental results corroborate that ViTs don’t demand deeper networks to achieve comparable accuracy of around 97% corresponding to heavily structured CNN models. We have also performed hardware deployment of our proposed lightweight ViT4Mal model on the Xilinx PYNQ Z1 FPGA board by applying specialized hardware optimizations such as quantization, loop pipelining, and array partitioning. ViT4Mal achieved an accuracy of ~94% and a 41x speedup compared to the original ViT model.