0% Complete
Home
/
13th International Conference on Computer and Knowledge Engineering
A large input-space-margin approach for adversarial training
Authors :
Reihaneh Nikouei
1
Mohammad Taheri
2
1- Department of Computer Science and Engineering, Shiraz University, Shiraz, Iran.
2- Department of Computer Science and Engineering, Shiraz University, Shiraz, Iran.
Keywords :
Adversarial attack،Large margin،Input space،Defense method
Abstract :
It is shown that machine learning models are vulnerable to adversarial attacks. Therefore, different defense methods such as adversarial training have been proposed to improve models’ robustness against these attacks. Some recent approaches proposed to structurally improve the robustness of the models. For example, large margin methods try to increase a margin, empty of instances, along decision boundaries that structurally increase necessary change to modify a training instance to an adversarial one. However, nonlinear large-margin models, maximize the margin in a high dimensional space although adversarial examples are generated with a little change in the original space. In this paper, a novel mixed approach is proposed, called LIM (Large Input Margin) to improve the robustness of the model by minimizing both structural and empirical risks. Specifically, both training and adversarial example generation are done based on a loss function to maximize the margin in the original feature space even in a non-linear model. The proposed method is evaluated with FGSM and PGD attacks on MNIST and CIFAR10 datasets. The experimental results show that LIM method outperforms the state-of-the-art defense methods significantly and improves adversarial robustness against FGSM and PGD attacks on both datasets.
Papers List
List of archived papers
Generating Hand-Written Symbols With Trajectory Planning Using A Robotic Arm
Arya Parvizi - Armin Salimi-Badr
An Overview of Regression Methods in Early Prediction of Movie Ratings
Houmaan Chamani - Zhivar Sourati Hassanzadeh - Behnam Bahrak
Deep Learning-Based Malaysian Sign Language (MSL) Recognition: Exploring the Impact of Color Spaces
Ervin Gubin Moung - Precilla Fiona Suwek - Maisarah Mohd Sufian - Valentino Liaw - Ali Farzamnia - Wei Leong Khong
Optimizing Question-Answering Framework Through Integration of Text Summarization Model and Third-Generation Generative Pre-Trained Transformer
Ervin Gubin Moung - Toh Sin Tong - Maisarah Mohd Sufian - Valentino Liaw - Ali Farzamnia - Farashazillah Yahya
Semi-automatic Detection of Persian Stopwords using FastText Library
Mohammad Dehghani - Mohammad Manthouri
Prediction of West Texas Intermediate Crude-oil Price Using Hybrid Attention-based Deep Neural Networks: A Comparative Study
Alireza Jahandoost - Mahboobeh Houshmand - Seyyed Abed Hosseini
Persis: A Persian Font Recognition Pipeline Using Convolutional Neural Networks
Mehrdad Mohammadian - Neda Maleki - Tobias Olsson - Fredrik Ahlgren
Fine-tuned Generative Adversarial Network-based Model for Medical Image Super-Resolution
Alireza Aghelan - Modjtaba Rouhani
Enhancing Vehicle Make and Model Recognition with 3D Attention Modules
Narges Semiromizadeh - Omid Nejati Manzari - Shahriar B. Shokouhi - Sattar Mirzakuchaki
City Intersection Clustering and Analysis Based on Traffic Time Series
Mohammad Aminazadeh - Fakhroddin Noorbehbahani
more
Samin Hamayesh - Version 41.5.3