SURVEY ON EFFICIENT ALGORITHMIC MODELS FOR ADVERSARIAL ATTACKS AND DEFENCES IN DEEP LEARNING
Sarala D.V1*, Thippeswamy G 2
1Assistant Professor, Department of Computer Science & Engg., Dayananda Sagar College of Engineering, Bangalore-560078, Karnataka, India.
2 Professor and Head, Department of Computer Science &Engg., BMSIT & M, Bangalore-560064, Karnataka, India.
*Corresponding Author: firstname.lastname@example.org.
Despite recent breakthroughs in a wide range of applications, machine learning models, particularly deep neural networks, have been demonstrated to be sensitive to adversarial assaults. Looking at these intelligent models from a security standpoint is critical; if the person/organization is uninformed, they must retrain the model and address the errors, which is both costly and time consuming. Attackers introduce carefully engineered perturbations into input, which are practically undetectable to humans but can lead models to make incorrect predictions. Hostile defense strategies are techniques for protecting models against adversarial input are called adversarial defense methods. These attacks can be performed on a range of models trained on images, text, time-series data. In our paper will discuss different kinds of attacks like White-Box attacks, Black-Box attacks etc on various models and also make them robust by using several defense approaches like adversarial training, Adversarial Detection, Input Denoising etc.
Keywords: Deep Learning Models; Adversarial Attacks; Adversarial Defenses.