Please wait ...
0% Complete
Home
/
13th International Conference on Computer and Knowledge Engineering
Adversarial Robustness Evaluation with Separation Index
Authors :
Bahareh Kaviani Baghbaderani
1
Afsaneh Hasanebrahimi
2
Ahmad Kalhor
3
Reshad Hosseini
4
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.
Papers List
List of archived papers
An Efficient Planning Method for Autonomous Navigation of a Wheeled-Robot based on Deep Reinforcement Learning
Ali Salimi Sadr - Mahdi Shahbazi Khojasteh - Hamed Malek - Armin Salimi-Badr
Forecasting El Niño Six Months in Advance Utilizing Augmented Convolutional Neural Network
Mohammad Naisipour - Iraj Saeedpanah - Arash Adib - Mohammad Hossein Neisi Pour
Virus-Antiviral Prediction Using Machine and Deep Learning Methods
Shayan Majidifar - Fatemeh Nasiri - Mohsen Hooshmand
Joint ADC-less Analog Demodulator and Decoder for Extended Binary (8, 4, 4) Hamming Channel Code
Mir Mahdi Safari - Jafar Pourrostam - Behzad Mozaffari Tazehkand
Delta-Audit: Explaining What Changes When Models Change
Arshia Hemmat - Afsane Fatemi
Delay Optimization of a Federated Learning-based UAV-aided IoT network
Hossein Mohammadi Firouzjaei - Javad Zeraatkar Moghaddam - Mehrdad Ardebilipour
Synthetic Trajectory Sharing Indoors under Privacy Constraints
Mahdi Soltanpour - Vahideh Moghtadaiee - Mina Alishahi
Object Detection on Detecting Skin Lesion using Dab-DETR
Sheida Shadman - Amirreza Rouhbakhshmeghrazi - Shayan Nalbandian - Bo Li - Shaghayegh Shadman - Malik Muhammad Owais Siddique
A New Time Series Approach in Churn Prediction with Discriminatory Intervals
Hedieh Ahmadi - Seyed Mohammad Hossein Hasheminejad
Computational Microscopy Based on Fourier Ptychography using Embedded Architecture
Rezvan Mir - Abedin Vahedian
more
Samin Hamayesh - Version 46.0.2