A Noise-Based Approach Augmented with Neural Cleanse and JPEG Compression to Counter Adversarial Attacks on Image Classification Systems

Adversarial attacks are now becoming quite a dangerous means of disrupting image processing systems that use machine learning methods for decision making. Therefore, developing effective countermeasures against adversarial attacks is becoming quite an important area of cybersecurity. The paper proposes a noise-based approach to countering adversarial attacks that is augmented with neural-cleanse and jpeg-compression technologies. The idea of the proposed approach is that adding noise distorts the effect of an adversarial attack, and neural cleaning and jpeg compression eliminate the consequences of such an effect. The paper examines the three most well-known types of adversarial attacks: Fast Gradient Sign Method, Zeroth Order Optimization and One Pixel Attack. These attacks manipulate input data, resulting in misclassification or incorrect predictions by exploiting high-frequency components that are undetectable to humans. The research was carried out on two datasets: MNIST-JPG and PC Parts Images. Two types of noise were used: Gaussian and Poisson. During the experiments, optimal parameters for these types of noise were found, ensuring maximum accuracy of image recognition after exposure to adversarial attacks.