Anshul Mittal
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
Anshul Mittal has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Swati Aggarwal
Faculty of Logistics, Molde University College, 6410 Molde, Norway
2 shared publications - Anshul Kumar Singh
Department of Computer Engineering, Netaji Subhas University of Technology, New Delhi 110078, India
1 shared publication - Chandra Prakash
Malaviya National Institute of Technology Jaipur
1 shared publication Christopher B. Hilbert
University of Tennessee, Chattanooga
1 shared publicationKidambi Sreenivas
University of Tennessee, Chattanooga
1 shared publicationLafayette K. Taylor
University of Tennessee, Chattanooga
1 shared publication
Latest Publications
- Open Access
Dynamic Programming-Based White Box Adversarial Attack for Deep Neural Networks
Recent studies have exposed the vulnerabilities of deep neural networks to some carefully perturbed input data. We propose a novel untargeted white box adversarial attack, the dynamic programming-based sub-pixel score method (SPSM) attack (DPSPSM), which is a variation of the traditional gradient-based white box adversarial approach that is limited by a fixed hamming distance using a dynamic programming-based structure. It is stimulated using a pixel score metric technique, the SPSM, which is introduced in this paper. In contrast to the conventional gradient-based adversarial attacks, which alter entire images almost imperceptibly, the DPSPSM is swift and offers the robustness of manipulating only a small number of input pixels. The presented algorithm quantizes the gradient update with a score generated for each pixel, incorporating contributions from each channel. The results show that the DPSPSM deceives the model with a success rate of 30.45% in the CIFAR-10 test set and 29.30% in the CIFAR-100 test set.
Open AccessDynamic Programming-Based White Box Adversarial Attack for Deep Neural Networks
Recent studies have exposed the vulnerabilities of deep neural networks to some carefully perturbed input data. We propose a novel untargeted white box adversarial attack, the dynamic programming-based sub-pixel score method (SPSM) attack (DPSPSM), which is a variation of the traditional gradient-based white box adversarial approach that is limited by a fixed hamming distance using a dynamic programming-based structure. It is stimulated using a pixel score metric technique, the SPSM, which is introduced in this paper. In contrast to the conventional gradient-based adversarial attacks, which alter entire images almost imperceptibly, the DPSPSM is swift and offers the robustness of manipulating only a small number of input pixels. The presented algorithm quantizes the gradient update with a score generated for each pixel, incorporating contributions from each channel. The results show that the DPSPSM deceives the model with a success rate of 30.45% in the CIFAR-10 test set and 29.30% in the CIFAR-100 test set.
- Open Access
- 1 February 2024
- Published by Elsevier in Journal of Open Innovation: Technology, Market, and Complexity
- Vol. 10 (1)
Futuristic hospitality conceptualized: DASH - Decentralized Autonomous and Smart Hotel system
- 1 February 2024
- Published by Elsevier in Journal of Open Innovation: Technology, Market, and Complexity
- Vol. 10 (1)
Open AccessFuturistic hospitality conceptualized: DASH - Decentralized Autonomous and Smart Hotel system
- Open Access
- 20 May 2020
- Published by Frontiers Media SA in Frontiers in Blockchain
- Vol. 3
Hyperparameter Optimization Using Sustainable Proof of Work in Blockchain
Hyperparameters are pivotal for machine learning models. The success of efficient calibration, often surpasses the results obtained by devising new approaches. Traditionally, human intervention is required to tune the models, however, this obtuse outlook restricts the proficiency and competence. Automating this crucial characteristic of learning sustainably, proffers a significant boost in performance and cost optimization. Blockchain technology has revolutionized industries utilizing its Proof-of-Work algorithms for consensus. This complicated solution generates a lot of useless computations across the nodes attached to the network and thus, fritters away a huge amount of precious energy. In this paper, we propose to exploit these inane computations for training deep learning models instead of calculating purposeless hash values, thus, suggesting a new consensus schema. This work distinguishes itself from other related works by capitalizing on the parallel processing prospects it generates for hyperparameter tuning of complex deep learning models. We address this aspect through the framework of Bayesian optimization which is an effective methodology for the global optimization of functions with expensive evaluations. We call our work, Proof of Deep Learning with Hyperparameter Optimization (PoDLwHO).
- 20 May 2020
- Published by Frontiers Media SA in Frontiers in Blockchain
- Vol. 3
Open AccessHyperparameter Optimization Using Sustainable Proof of Work in Blockchain
Hyperparameters are pivotal for machine learning models. The success of efficient calibration, often surpasses the results obtained by devising new approaches. Traditionally, human intervention is required to tune the models, however, this obtuse outlook restricts the proficiency and competence. Automating this crucial characteristic of learning sustainably, proffers a significant boost in performance and cost optimization. Blockchain technology has revolutionized industries utilizing its Proof-of-Work algorithms for consensus. This complicated solution generates a lot of useless computations across the nodes attached to the network and thus, fritters away a huge amount of precious energy. In this paper, we propose to exploit these inane computations for training deep learning models instead of calculating purposeless hash values, thus, suggesting a new consensus schema. This work distinguishes itself from other related works by capitalizing on the parallel processing prospects it generates for hyperparameter tuning of complex deep learning models. We address this aspect through the framework of Bayesian optimization which is an effective methodology for the global optimization of functions with expensive evaluations. We call our work, Proof of Deep Learning with Hyperparameter Optimization (PoDLwHO).
- 1 April 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 348-353
A framework for human recognition using a multimodel Gait analysis approach
Gait analysis applications are not only limited to medical, rehabilitation and sports, but it can also play a decisive role in security and surveillance as a behavioral biometric factor. Gait recognition is non-invasive and doesn't need any cooperation from subject in case of video surveillance. This paper presents a framework for human recognition based on gait without using markers or sensors using multimodel approach. The experiment presented in this paper was initially performed on 10 subjects, whose data were recorded at Raman Lab, MNIT Jaipur. In order to cross validate our approach, we have also used a standard gait database CASIA B.
- 1 April 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 348-353
A framework for human recognition using a multimodel Gait analysis approach
Gait analysis applications are not only limited to medical, rehabilitation and sports, but it can also play a decisive role in security and surveillance as a behavioral biometric factor. Gait recognition is non-invasive and doesn't need any cooperation from subject in case of video surveillance. This paper presents a framework for human recognition based on gait without using markers or sensors using multimodel approach. The experiment presented in this paper was initially performed on 10 subjects, whose data were recorded at Raman Lab, MNIT Jaipur. In order to cross validate our approach, we have also used a standard gait database CASIA B.