DEFENDING DEEP CNNS AGAINST ADVERSARIAL ATTACKS: RECENT TECHNIQUES AND TRENDS.

Abstract

Adversarial attacks are a big problem for deep neural networks (DNNs), especially when it comes to image classification tasks where even small changes can lead to big mistakes.  This weakness makes deep convolutional neural networks (DCNNs), generative adversarial networks (GANs), and new architectures like Vision Transformers less reliable.  In the last few years, there have been a lot of new ways to attack, from gradient-based methods like FGSM and PGD to optimization-based, patch, and backdoor attacks.  As a result, defense mechanisms have developed in many areas, such as adversarial training, input transformations, detection frameworks, and generative purification methods.  Even with these improvements, no one defense has been shown to be strong enough to work in all situations. Most methods have to choose between accuracy, scalability, and resistance to adaptive adversaries.  To solve this problem, researchers are looking into optimization-driven methods to make systems more robust and improve training efficiency. These methods include biologically inspired metaheuristics like Sparrow Search and Cuckoo Optimization, as well as modern deep learning optimizers.  Benchmark datasets like MNIST, Fashion-MNIST, and CIFAR-10 have become very important for testing both attacks and defenses. They give us a standard way to measure accuracy, precision, recall, and sensitivity when things go wrong.  This review brings together changes from 2018 to 2023, with a focus on optimization-enhanced training and the different types of adversarial strategies and defense paradigms.  Moreover, we suggest a hybrid defense framework that combines adversarial training, metaheuristic optimization, and lightweight input filtering to protect against both white-box and black-box attacks at multiple levels.  The goal is to get a full picture of the adversarial landscape, find research gaps that keep coming up, and find ways to make deep learning models for image classification that are more resistant to attacks.