Detecting malicious Uniform Resource Locators(URLs)is crucially important to prevent attackers from committing *** researches have investigated the role of machine learning(ML)models to detect malicious *** using ML a...
详细信息
Detecting malicious Uniform Resource Locators(URLs)is crucially important to prevent attackers from committing *** researches have investigated the role of machine learning(ML)models to detect malicious *** using ML algorithms,rst,the features of URLs are extracted,and then different ML models are *** limitation of this approach is that it requires manual feature engineering and it does not consider the sequential patterns in the ***,deep learning(DL)models are used to solve these issues since they are able to perform featureless ***,DL models give better accuracy and generalization to newly designed URLs;however,the results of our study show that these models,such as any other DL models,can be susceptible to adversarial *** this paper,we examine the robustness of these models and demonstrate the importance of considering this susceptibility before applying such detection systems in real-world *** propose and demonstrate a black-box attack based on scoring functions with greedy search for the minimum number of perturbations leading to a *** attack is examined against different types of convolutional neural networks(CNN)-based URL classiers and it causes a tangible decrease in the accuracy with more than 56%reduction in the accuracy of the best classier(among the selected classiers for this work).Moreover,adversarial training shows promising results in reducing the inuence of the attack on the robustness of the model to less than 7%on average.
We are very glad to welcome our colleagues-young scientists, researchers and practitioners to the 9-Th IEEE Open Conference of Electrical, Electronic and Information sciences (eStream'2022), held in Vilnius Gedimi...
详细信息
Due to the strong data fitting ability of deep learning, the use of deep learning for quantitative trading has gradually sprung up in recent years. As a classical problem of quantitative trading, Stock Trend Predictio...
详细信息
We study the sublinear multivariate mean estimation problem in d-dimensional Euclidean space. Specifically, we aim to find the mean µ of a ground point set A, which minimizes the sum of squared Euclidean distance...
详细信息
This paper investigates privacy issues in distributed resource allocation over directed networks, where each agent holds a private cost function and optimizes its decision subject to a global coupling constraint throu...
详细信息
Detecting attacks using encrypted signals is challenging since encryption hides its information content. We present a novel mechanism for anomaly detection over Learning with Errors (LWE) encrypted signals without usi...
详细信息
The development of practical Brain-computer Interface (BCI) systems has been hindered by significant issues related to data, specifically the lack of sufficient data needed for training. To address this challenge, gen...
The development of practical Brain-computer Interface (BCI) systems has been hindered by significant issues related to data, specifically the lack of sufficient data needed for training. To address this challenge, generating synthetic data that mimics real recorded data has been proposed to augment the real data. One promising technique for data augmentation is through the use of Generative Adversarial Networks (GANs), which have been successfully applied in many other fields. This paper proposes a novel GAN-based approach for generating synthetic spectrum images of Motor Imagery (MI) Electroencephalogram (EEG). The proposed GAN is examined with two Convolutional Neural Network (CNN) architectures in the context of MI classification. Using the public dataset BCI competition IV, our findings reveal that the generated EEG spectrum images using GANs exhibit temporal, spectral, and spatial characteristics similar to the real ones. The average classification accuracy of right-hand versus left-hand MI using the proposed GAN/CNN models has improved to 76.71% with an enhancement of 2.5% in comparison to using the CNN applied to the real data only. These results suggest that using GANs could improve MI BCI systems with limited data.
This paper presents a refined complexity calculus model: r-Complexity, a new asymptotic notation that offers better complexity feedback for similar programs than the traditional Bachmann-Landau notation, providing sub...
详细信息
Despite the recent success of Graph Neural Networks (GNNs), it remains challenging to train GNNs on large-scale graphs due to neighbor explosions. As a remedy, distributed computing becomes a promising solution by lev...
详细信息
This paper aims to contribute to the conceptual debate on the connection between social innovation and social entrepreneurship,considering the role of the‘social’within this *** by a systematic literature review(SLR...
详细信息
This paper aims to contribute to the conceptual debate on the connection between social innovation and social entrepreneurship,considering the role of the‘social’within this *** by a systematic literature review(SLR)with an in-depth analysis of 34 articles from Scopus-indexed and Web of science databases journals,this paper identifies,analyzes and describes the difficulties and opportunities in the social innovation and social entrepreneurship *** is known about the link between both concepts and the influence of the‘social’in their development and *** SLR was conducted to identify and describe definitions and *** show that the connection between social innovation and social entrepreneurship is in its take-off phase,but it still is a fragmented field with a huge lack of ***,it will be important to see where the field will head,as this paper aims to be a first step in the understanding of social innovation and social entrepreneurship through a collective and integrated perspective,providing an elucidation of the different perspectives of the literature.
暂无评论