scholarly journals An Unsupervised Approach for Detecting Group Shilling Attacks in Recommender Systems Based on Topological Potential and Group Behaviour Features

2021 ◽  
Vol 2021 ◽  
pp. 1-18
Author(s):  
Hongyun Cai ◽  
Fuzhi Zhang
Keyword(s):  
Recommender Systems ◽  
Detection Method ◽  
Potential Method ◽  
Detection Methods ◽  
Clustering Method ◽  
Group Behaviour ◽  
The Past ◽  
Group Members ◽  
Unsupervised Approach ◽  
Individual Features

To protect recommender systems against shilling attacks, a variety of detection methods have been proposed over the past decade. However, these methods focus mainly on individual features and rarely consider the lockstep behaviours among attack users, which suffer from low precision in detecting group shilling attacks. In this work, we propose a three-stage detection method based on strong lockstep behaviours among group members and group behaviour features for detecting group shilling attacks. First, we construct a weighted user relationship graph by combining direct and indirect collusive degrees between users. Second, we find all dense subgraphs in the user relationship graph to generate a set of suspicious groups by introducing a topological potential method. Finally, we use a clustering method to detect shilling groups by extracting group behaviour features. Extensive experiments on the Netflix and sampled Amazon review datasets show that the proposed approach is effective for detecting group shilling attacks in recommender systems, and the F1-measure on two datasets can reach over 99 percent and 76 percent, respectively.

scholarly journals Detecting Shilling Attacks with Automatic Features from Multiple Views

2019 ◽  
Vol 2019 ◽  
pp. 1-13 ◽  
Author(s):  
Yaojun Hao ◽  
Fuzhi Zhang ◽  
Jian Wang ◽  
Qingshan Zhao ◽  
Jianfang Cao
Keyword(s):  
Principal Component Analysis ◽  
Recommender Systems ◽  
Detection Method ◽  
Principal Component ◽  
Component Analysis ◽  
Experimental Results ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Multiple Views ◽  
Fine Grained

Due to the openness of the recommender systems, the attackers are likely to inject a large number of fake profiles to bias the prediction of such systems. The traditional detection methods mainly rely on the artificial features, which are often extracted from one kind of user-generated information. In these methods, fine-grained interactions between users and items cannot be captured comprehensively, leading to the degradation of detection accuracy under various types of attacks. In this paper, we propose an ensemble detection method based on the automatic features extracted from multiple views. Firstly, to collaboratively discover the shilling profiles, the users’ behaviors are analyzed from multiple views including ratings, item popularity, and user-user graph. Secondly, based on the data preprocessed from multiple views, the stacked denoising autoencoders are used to automatically extract user features with different corruption rates. Moreover, the features extracted from multiple views are effectively combined based on principal component analysis. Finally, according to the features extracted with different corruption rates, the weak classifiers are generated and then integrated to detect attacks. The experimental results on the MovieLens, Netflix, and Amazon datasets indicate that the proposed method can effectively detect various attacks.

scholarly journals Cloud detection for MIPAS using singular vector decomposition

2009 ◽  
Vol 2 (2) ◽  
pp. 1185-1219
Author(s):  
J. Hurley ◽  
A. Dudhia ◽  
R. G. Grainger
Keyword(s):  
Climate Models ◽  
Singular Vector ◽  
Detection Method ◽  
Michelson Interferometer ◽  
Detection Methods ◽  
Cloud Detection ◽  
Radiative Balance ◽  
The Past ◽  
Vector Decomposition ◽  
Atmospheric Sounding

Abstract. Clouds are increasingly recognised for their influence on the radiative balance of the Earth and the implications that they have on possible climate change, as well as in air pollution and acid-rain production. However, clouds remain a major source of uncertainty in climate models. Satellite-borne high-resolution limb sounders, such as the Michelson Interferometer for Passive Atmospheric Sounding (MIPAS) onboard ENVISAT, provide information on clouds, especially optically thin clouds, which have been difficult to observe in the past. The aim of this work is to develop, implement and test a reliable cloud detection method for infrared spectra measured by MIPAS. Current MIPAS cloud detection methods used operationally have been developed to detect thick cloud filling more than 30% of the measurement field-of-view (FOV). In order to resolve thin clouds, a new detection method using Singular Vector Decomposition (SVD) is formulated and tested. A rigorous comparison of the current operational and newly-developed detection methods for MIPAS is carried out – and the new SVD detection method has been proven to be much more reliable than the current operational method, and very sensitive even to thin clouds only marginally filling the MIPAS FOV.

scholarly journals Cloud detection for MIPAS using singular vector decomposition

2009 ◽  
Vol 2 (2) ◽  
pp. 533-547 ◽  
Author(s):  
J. Hurley ◽  
A. Dudhia ◽  
R. G. Grainger
Keyword(s):  
Singular Vector ◽  
Detection Method ◽  
Michelson Interferometer ◽  
High Spectral Resolution ◽  
Detection Methods ◽  
Cloud Detection ◽  
The Past ◽  
Vector Decomposition ◽  
Atmospheric Sounding ◽  
Thin Cloud

Abstract. Satellite-borne high-spectral-resolution limb sounders, such as the Michelson Interferometer for Passive Atmospheric Sounding (MIPAS) onboard ENVISAT, provide information on clouds, especially optically thin clouds, which have been difficult to observe in the past. The aim of this work is to develop, implement and test a reliable cloud detection method for infrared spectra measured by MIPAS. Current MIPAS cloud detection methods used operationally have been developed to detect cloud effective filling more than 30% of the measurement field-of-view (FOV), under geometric and optical considerations – and hence are limited to detecting fairly thick cloud, or large physical extents of thin cloud. In order to resolve thin clouds, a new detection method using Singular Vector Decomposition (SVD) is formulated and tested. This new SVD detection method has been applied to a year's worth of MIPAS data, and qualitatively appears to be more sensitive to thin cloud than the current operational method.

scholarly journals CNN Feature-Based Image Copy Detection with Contextual Hash Embedding

Mathematics ◽  
2020 ◽  
Vol 8 (7) ◽  
pp. 1172
Author(s):  
Zhili Zhou ◽  
Meimin Wang ◽  
Yi Cao ◽  
Yuecheng Su
Keyword(s):  
Detection Method ◽  
Superior Performance ◽  
Detection Methods ◽  
Copy Detection ◽  
Visual Words ◽  
The Past ◽  
Index File ◽  
Image Copy Detection ◽  
Feature Based ◽  
Deep Learning Features

As one of the important techniques for protecting the copyrights of digital images, content-based image copy detection has attracted a lot of attention in the past few decades. The traditional content-based copy detection methods usually extract local hand-crafted features and then quantize these features to visual words by the bag-of-visual-words (BOW) model to build an inverted index file for rapid image matching. Recently, deep learning features, such as the features derived from convolutional neural networks (CNN), have been proven to outperform the hand-crafted features in many applications of computer vision. However, it is not feasible to directly apply the existing global CNN features for copy detection, since they are usually sensitive to partial content-discarded attacks, such as copping and occlusion. Thus, we propose a local CNN feature-based image copy detection method with contextual hash embedding. We first extract the local CNN features from images and then quantize them to visual words to construct an index file. Then, as the BOW quantization process decreases the discriminability of these features to some extent, a contextual hash sequence is captured from a relatively large region surrounding each CNN feature and then is embedded into the index file to improve the feature’s discriminability. Extensive experimental results demonstrate that the proposed method achieves a superior performance compared to the related works in the copy detection task.

scholarly journals A Consensus Clustering Method for Clustering Social Networks

2020 ◽  
Vol 8 (1) ◽  
pp. 254-271
Author(s):  
Masoumeh Kheirkhahzadeh ◽  
Morteza Analoui
Keyword(s):  
Community Detection ◽  
Detection Method ◽  
Detection Methods ◽  
Consensus Clustering ◽  
Clustering Method ◽  
Normalized Mutual Information ◽  
Wide Range ◽  
The Common ◽  
Accuracy Measures ◽  
Artificial Datasets

Detecting Communities in networks is one of the appealing fields in computer science. A wide range of methods are proposed for this problem. These methods employ different strategies and optimization functions to detect communities (or clusters). Therefore, it seems a good idea to combine these strategies to take advantage of the strengths of the methods and overcome their problems. This is the idea behind consensus clustering technique which combines several clustering results into one. In this paper, we propose a very good-performing method based on consensus clustering to detect communities of a network. Our method, called “Azar”, employed several community detection methods as base methods. Then Azar generates a new compressed network based on the common views of the used base methods and, gives this new compressed network to the last community detection method to find the final partition. We evaluate our approach by employing real and artificial datasets. The implementation results compare the base methods with Azar according to accuracy measures such as modularity and Normalized Mutual Information (NMI). The results show the good-performing behavior of Azar even for the most difficult networks. The results show the brilliant power of Azar in comparison with all the other methods.

Automated Detection of Pin Defects on Counterfeit Microelectronics

2018 ◽  
Author(s):  
Pallabi Ghosh ◽  
Domenic Forte ◽  
Damon L. Woodard ◽  
Rajat Subhra Chakraborty
Keyword(s):  
Integrated Circuits ◽  
Depth Map ◽  
Optical Microscope ◽  
Automated Detection ◽  
Detection Methods ◽  
Global Supply Chains ◽  
Subject Matter Experts ◽  
Security Breaches ◽  
The Past ◽  
Skilled Subject

Abstract Counterfeit electronics constitute a fast-growing threat to global supply chains as well as national security. With rapid globalization, the supply chain is growing more and more complex with components coming from a diverse set of suppliers. Counterfeiters are taking advantage of this complexity and replacing original parts with fake ones. Moreover, counterfeit integrated circuits (ICs) may contain circuit modifications that cause security breaches. Out of all types of counterfeit ICs, recycled and remarked ICs are the most common. Over the past few years, a plethora of counterfeit IC detection methods have been created; however, most of these methods are manual and require highly-skilled subject matter experts (SME). In this paper, an automated bent and corroded pin detection methodology using image processing is proposed to identify recycled ICs. Here, depth map of images acquired using an optical microscope are used to detect bent pins, and segmented side view pin images are used to detect corroded pins.

Can Groups Assert That P?

2019 ◽  
pp. 326-344
Author(s):  
Deborah Tollefsen
Keyword(s):  
Common Ground ◽  
Speech Act ◽  
Single Individual ◽  
Constitutive Rule ◽  
The Past ◽  
Group Members ◽  
The Common ◽  
Declarative Statement ◽  
John Macfarlane

When a group or institution issues a declarative statement, what sort of speech act is this? Is it the assertion of a single individual (perhaps the group’s spokesperson or leader) or the assertion of all or most of the group members? Or is there a sense in which the group itself asserts that p? If assertion is a speech act, then who is the actor in the case of group assertion? These are the questions this chapter aims to address. Whether groups themselves can make assertions or whether a group of individuals can jointly assert that p depends, in part, on what sort of speech act assertion is. The literature on assertion has burgeoned over the past few years, and there is a great deal of debate regarding the nature of assertion. John MacFarlane has helpfully identified four theories of assertion. Following Sandy Goldberg, we can call these the attitudinal account, the constitutive rule account, the common-ground account, and the commitment account. I shall consider what group assertion might look like under each of these accounts and doing so will help us to examine some of the accounts of group assertion (often presented as theories of group testimony) on offer. I shall argue that, of the four accounts, the commitment account can best be extended to make sense of group assertion in all its various forms.

scholarly journals PRATD: A Phased Remote Access Trojan Detection Method with Double-Sided Features

Electronics ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1894
Author(s):  
Chun Guo ◽  
Zihua Song ◽  
Yuan Ping ◽  
Guowei Shen ◽  
Yuhei Cui ◽  
...  
Keyword(s):  
False Positive ◽  
Detection Method ◽  
False Positive Rate ◽  
True Positive Rate ◽  
Remote Access ◽  
Detection Methods ◽  
Security Threats ◽  
True Positive ◽  
Trojan Detection ◽  
Positive Rate

Remote Access Trojan (RAT) is one of the most terrible security threats that organizations face today. At present, two major RAT detection methods are host-based and network-based detection methods. To complement one another’s strengths, this article proposes a phased RATs detection method by combining double-side features (PRATD). In PRATD, both host-side and network-side features are combined to build detection models, which is conducive to distinguishing the RATs from benign programs because that the RATs not only generate traffic on the network but also leave traces on the host at run time. Besides, PRATD trains two different detection models for the two runtime states of RATs for improving the True Positive Rate (TPR). The experiments on the network and host records collected from five kinds of benign programs and 20 famous RATs show that PRATD can effectively detect RATs, it can achieve a TPR as high as 93.609% with a False Positive Rate (FPR) as low as 0.407% for the known RATs, a TPR 81.928% and FPR 0.185% for the unknown RATs, which suggests it is a competitive candidate for RAT detection.

scholarly journals Detection of Movement Events of Long-Track Speed Skating Using Wearable Inertial Sensors

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3649
Author(s):  
Yosuke Tomita ◽  
Tomoki Iizuka ◽  
Koichi Irisawa ◽  
Shigeyuki Imura
Keyword(s):  
Gold Standard ◽  
Detection Method ◽  
Standard Measure ◽  
Detection Methods ◽  
Phase Identification ◽  
Foot Pressure ◽  
Pressure System ◽  
Speed Skating ◽  
Stance Time ◽  
Integrated Detection

Inertial measurement units (IMUs) have been used increasingly to characterize long-track speed skating. We aimed to estimate the accuracy of IMUs for use in phase identification of long-track speed skating. Twelve healthy competitive athletes on a university long-track speed skating team participated in this study. Foot pressure, acceleration and knee joint angle were recorded during a 1000-m speed skating trial using the foot pressure system and IMUs. The foot contact and foot-off timing were identified using three methods (kinetic, acceleration and integrated detection) and the stance time was also calculated. Kinetic detection was used as the gold standard measure. Repeated analysis of variance, intra-class coefficients (ICCs) and Bland-Altman plots were used to estimate the extent of agreement between the detection methods. The stance time computed using the acceleration and integrated detection methods did not differ by more than 3.6% from the gold standard measure. The ICCs ranged between 0.657 and 0.927 for the acceleration detection method and 0.700 and 0.948 for the integrated detection method. The limits of agreement were between 90.1% and 96.1% for the average stance time. Phase identification using acceleration and integrated detection methods is valid for evaluating the kinematic characteristics during long-track speed skating.

Sign in / Sign up

Export Citation Format

Share Document