• Supantha Sarker
• Muntasir Mamun Siam
• Shayok Ul Islam
• Md Monir Hossain
• Asibur Rahman Akash

Machine Learning models are used for a variety of tasks, such as picture categorization, virus detection, and network intrusion detection. However, subsequent studies have shown that even the most advanced deep neural networks, which excel at such tasks, are subject to a bug. Adversarial Examples are a type of harmful input. These are non-random inputs that are nearly indistinguishable from natural data but are incorrectly categorized. In this paper, we attempt to investigate the presence of adversarial instances and highlight some of the numerous approaches developed to exploit deep neural network flaws. over time and give an analysis of such attacks as a subset of ImageNet's visually distinguishable classifications.

Adversarial Examples, virus detection, Machine Learning, deep neural networks.

"Attack Analysis of Face Recognition Authentication Systems Using Basic Iterative Method (BIM)", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 5, page no.g688-g697, May-2022, Available :http://www.jetir.org/papers/JETIR2205781.pdf

"Attack Analysis of Face Recognition Authentication Systems Using Basic Iterative Method (BIM)", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 5, page no. ppg688-g697, May-2022, Available at : http://www.jetir.org/papers/JETIR2205781.pdf