International Conference on Computer and Knowledge Engineering

Home / 13th International Conference on Computer and Knowledge Engineering

Adversarial Robustness Evaluation with Separation Index

Authors :

Bahareh Kaviani Baghbaderani¹ Afsaneh Hasanebrahimi² Ahmad Kalhor³ Reshad Hosseini⁴

1- School of Electrical and Computer Engineering, College of Engineering, University of Tehran 2- School of Electrical and Computer Engineering, College of Engineering, University of Tehran 3- School of Electrical and Computer Engineering, College of Engineering, University of Tehran 4- School of Electrical and Computer Engineering, College of Engineering, University of Tehran

Keywords :

Separation Index،Robustness Evaluation،Variational Autoencoder

Abstract :

The paper introduces a method to assess the robustness of deep neural networks against adversarial attacks. It employs a geometric-based separation metric called the Separation Index, which measures the distance between data points with distinct labels within the latent space of variational autoencoders utilized for classification tasks. The Separation Index quantifies the degree of data separation by comparing each data point with its neighboring data points. A higher value signifies greater separation between different classes, thus ensuring enhanced robustness. This approach yields dependable results when confronted with gradientbased adversarial attacks, including FGSM, R-FGSM, MI-FGSM, and PGD, under both white-box and blackbox conditions.