Dwarkoba P. Gaikwad

Work place: AISSMS College of Engineering, Pune, 411001, India

E-mail: dpgaikwad@aissmscoe.com


Research Interests: Electrical Engineering, Engineering, Computational Engineering


Dr. Dwarkoba. P. Gaikwad received his B.E. degree in Computer Science and Engineering from Shri Guru Gobind Singhji Institute of Engineering and Technology, Nanded, Maharashtra, India and M.S. degrees in Electrical Engineering from College of Engineering, Pune, Maharashtra, India in 1996 and 2006 respectively. He has been awarded Ph.D. degree in Computer Science and Engineering in 2017. Currently, he is working as an Associate Professor and Head of Department of Computer Engineering in AISSMS College of Engineering, Pune, Maharashtra, India. He has published more than 40 papers in International journal and conferences. He received best researcher award in International Scientist Award Conference held at Vishakhapatnam, India.


Author Articles
Towards Query Efficient and Derivative Free Black Box Adversarial Machine Learning Attack

By Amir F. Mukeri Dwarkoba P. Gaikwad

DOI: https://doi.org/10.5815/ijigsp.2022.02.02, Pub. Date: 8 Apr. 2022

While deep learning has shown phenomenal success in many critical applications such as in autonomous driving and medical diagnosis, it is vulnerable to black box adversarial machine learning attacks. Objective of these attacks is to mislead a classifier in making mistakes. Hard Label attacks are those in which an adversary has access only to the top-1 prediction label and has no knowledge about model parameters or gradient loss. Secondly, for security concerns, the number of model queries that an attacker can perform for evaluation are restricted. In this paper, we propose a novel nature-inspired optimization algorithm for generating adversarial examples. Proposed algorithm is derivative-free, meta-heuristic algorithm. It searches for optimum adversarial examples in high-dimensional image space using simple arithmetic operations inspired by Brownian motion of molecules in fluids and gases. Experiments with CIFAR-10 image dataset yielded encouraging results with a query budget of less than 1000 and with a minimal distortion to original image. Its performance was determined to be comparable and exceeded in some cases compared to previous state of the art attacks.

[...] Read more.
Other Articles