DeepAI AI Chat
Log In Sign Up

A Deep Marginal-Contrastive Defense against Adversarial Attacks on 1D Models

by   Mohammed Hassanin, et al.

Deep learning algorithms have been recently targeted by attackers due to their vulnerability. Several research studies have been conducted to address this issue and build more robust deep learning models. Non-continuous deep models are still not robust against adversarial, where most of the recent studies have focused on developing attack techniques to evade the learning process of the models. One of the main reasons behind the vulnerability of such models is that a learning classifier is unable to slightly predict perturbed samples. To address this issue, we propose a novel objective/loss function, the so-called marginal contrastive, which enforces the features to lie under a specified margin to facilitate their prediction using deep convolutional networks (i.e., Char-CNN). Extensive experiments have been conducted on continuous cases (e.g., UNSW NB15 dataset) and discrete ones (i.e, eight-large-scale datasets [32]) to prove the effectiveness of the proposed method. The results revealed that the regularization of the learning process based on the proposed loss function can improve the performance of Char-CNN.


page 1

page 2

page 3

page 4


On Learning Contrastive Representations for Learning with Noisy Labels

Deep neural networks are able to memorize noisy labels easily with a sof...

Mitigating the Impact of Adversarial Attacks in Very Deep Networks

Deep Neural Network (DNN) models have vulnerabilities related to securit...

The Vulnerabilities of Graph Convolutional Networks: Stronger Attacks and Defensive Techniques

Graph deep learning models, such as graph convolutional networks (GCN) a...

Understanding Adversarial Robustness: The Trade-off between Minimum and Average Margin

Deep models, while being extremely versatile and accurate, are vulnerabl...

Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibration

Previous works have extensively studied the transferability of adversari...

Spatio-Temporal Graph Contrastive Learning

Deep learning models are modern tools for spatio-temporal graph (STG) fo...

Adversarial Defense Via Local Flatness Regularization

Adversarial defense is a popular and important research area. Due to its...