Pub Date : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892056
Weidong Liu, Quanping Zhang, Wenbo Qiao
With the complexity of patent transformation scenarios, the roles of users have become more diverse. Therefore, how to discover the roles of different users in the patent transformation scenarios has become a hot issue. In the process of patent transformation, the behaviors of each user are regular, historical behavior has an impact on the current behavior. Because the Hawkes processes can take into account the characteristic of self-exciting among behaviors, we explored the Dirichlet Mixture model of Hawkes Processes based on variational inference to cluster users for user roles discovery. In this model, different Hawkes processes correspond to different user types. Dirichlet distribution is used as the prior distribution of user clusters. The dependence of current behavior on historical behavior is expressed as intensity function. The variational inference is used to learn the model. The model is evaluated by Precision, Recall and F-measure, which shows that our model has good accuracy.
{"title":"Dirichlet Mixture Model of Hawkes Processes Based Patent User Role Discovery Model","authors":"Weidong Liu, Quanping Zhang, Wenbo Qiao","doi":"10.1109/IJCNN55064.2022.9892056","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892056","url":null,"abstract":"With the complexity of patent transformation scenarios, the roles of users have become more diverse. Therefore, how to discover the roles of different users in the patent transformation scenarios has become a hot issue. In the process of patent transformation, the behaviors of each user are regular, historical behavior has an impact on the current behavior. Because the Hawkes processes can take into account the characteristic of self-exciting among behaviors, we explored the Dirichlet Mixture model of Hawkes Processes based on variational inference to cluster users for user roles discovery. In this model, different Hawkes processes correspond to different user types. Dirichlet distribution is used as the prior distribution of user clusters. The dependence of current behavior on historical behavior is expressed as intensity function. The variational inference is used to learn the model. The model is evaluated by Precision, Recall and F-measure, which shows that our model has good accuracy.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115715719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892004
Boli Fang, Zhenghao Peng, Hao Sun, Qin Zhang
In this paper we propose Multi-Agent Proxy Proximal Policy Optimization (MA3PO), a novel multi-agent deep reinforcement learning algorithm that tackles the challenge of cooperative continuous multi-agent control. Our method is driven by the observation that most existing multi-agent reinforcement learning algorithms mainly focus on discrete state/action spaces and are thus computationally infeasible when extended to environments with continuous state/action spaces. To address the issue of computational complexity and to better model intra-agent collaboration, we make use of the recently successful Proximal Policy Optimization algorithm that effectively explores of continuous action spaces, and incorporate the notion of intrinsic motivation via meta-gradient methods so as to stimulate the behavior of individual agents in cooperative multi-agent settings. Towards these ends, we design proxy rewards to quantify the effect of individual agent-level intrinsic motivation onto the team-level reward, and apply meta-gradient methods to leverage such an addition so that our algorithm can learn the team-level cumulative reward effectively. Experiments on various multi-agent reinforcement learning benchmark environments with continuous action spaces demonstrate that our algorithm is not only comparable with the existing state-of-the-art benchmarks, but also significantly reduces training time complexity.
{"title":"Meta Proximal Policy Optimization for Cooperative Multi-Agent Continuous Control","authors":"Boli Fang, Zhenghao Peng, Hao Sun, Qin Zhang","doi":"10.1109/IJCNN55064.2022.9892004","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892004","url":null,"abstract":"In this paper we propose Multi-Agent Proxy Proximal Policy Optimization (MA3PO), a novel multi-agent deep reinforcement learning algorithm that tackles the challenge of cooperative continuous multi-agent control. Our method is driven by the observation that most existing multi-agent reinforcement learning algorithms mainly focus on discrete state/action spaces and are thus computationally infeasible when extended to environments with continuous state/action spaces. To address the issue of computational complexity and to better model intra-agent collaboration, we make use of the recently successful Proximal Policy Optimization algorithm that effectively explores of continuous action spaces, and incorporate the notion of intrinsic motivation via meta-gradient methods so as to stimulate the behavior of individual agents in cooperative multi-agent settings. Towards these ends, we design proxy rewards to quantify the effect of individual agent-level intrinsic motivation onto the team-level reward, and apply meta-gradient methods to leverage such an addition so that our algorithm can learn the team-level cumulative reward effectively. Experiments on various multi-agent reinforcement learning benchmark environments with continuous action spaces demonstrate that our algorithm is not only comparable with the existing state-of-the-art benchmarks, but also significantly reduces training time complexity.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124407428","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892559
Hao Liu, H. Qiao, Xiaoyu Shi, Mingsheng Shang
Recently, user-provided reviews have been identified as an essential resource to improve user and item representation in recommender systems. Previous methods focus on the review-based recommender typically leverages symmetric networks to process user and item reviews. However, in reality, these two sets of reviews are markedly different: a user's reviews reflect the experience of buying diverse items and show their heterogeneous interests. In contrast, an item's reviews emphasize the quality of the specific item. Thus an item's reviews are usually homogeneous. This paper seeks to explore the aspect of review difference in the review-based recommendation framework. We propose a novel asymmetric neural network model that accurately learns the user and item representation by identifying this critical difference. We focus on capturing the dynamic change of user interest for the user-aspect reviews via modeling the temporal information into the conventional neural network(CNN). On the other side, we try to identify a specific item's essential yet essential features by utilizing the self-attention neural network. Finally, a factorization machine (FM) is adopted to finish the rating prediction task, where the user and item IDs are encoded as supplementary review embedding. We conduct comprehensive experiments on four Amazon datasets, and the experimental results show that our proposed model consistently outperforms several state-of-the-art methods.
{"title":"Aspect-aware Asymmetric Representation Learning Network for Review-based Recommendation","authors":"Hao Liu, H. Qiao, Xiaoyu Shi, Mingsheng Shang","doi":"10.1109/IJCNN55064.2022.9892559","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892559","url":null,"abstract":"Recently, user-provided reviews have been identified as an essential resource to improve user and item representation in recommender systems. Previous methods focus on the review-based recommender typically leverages symmetric networks to process user and item reviews. However, in reality, these two sets of reviews are markedly different: a user's reviews reflect the experience of buying diverse items and show their heterogeneous interests. In contrast, an item's reviews emphasize the quality of the specific item. Thus an item's reviews are usually homogeneous. This paper seeks to explore the aspect of review difference in the review-based recommendation framework. We propose a novel asymmetric neural network model that accurately learns the user and item representation by identifying this critical difference. We focus on capturing the dynamic change of user interest for the user-aspect reviews via modeling the temporal information into the conventional neural network(CNN). On the other side, we try to identify a specific item's essential yet essential features by utilizing the self-attention neural network. Finally, a factorization machine (FM) is adopted to finish the rating prediction task, where the user and item IDs are encoded as supplementary review embedding. We conduct comprehensive experiments on four Amazon datasets, and the experimental results show that our proposed model consistently outperforms several state-of-the-art methods.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123079732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892442
Katarzyna Filus, J. Domańska
Deep Convolutional Neural Networks (CNNs) still lack interpretability and are often treated as miraculous blackbox machines. Therefore, when an intelligent system fails, it is usually difficult to troubleshoot the problems. Among others, these issues can be caused by incorrect decisions of the CNN classifier. The other reason can be selective “blindness” of the CNN - caused by an insufficient generalization of the convolutional feature extractor. To better understand the CNN decisions, methods from the Class Activation Mapping (CAM) family have been introduced. In contrast to CAM techniques, which focus on the model's predictions (thus a classifier), we propose a simple yet informative way to visualize network activation - Network Activation Mapping (NAM). Our method targets the most important part of the CNN - a convolutional feature extractor. Opposed to CAM methods, NAM is class-and classifier-independent and provides insight into what the neural network focuses on during the feature extraction process and what features it finds the most prominent in the examined image. Due to the classifier-independence, it can be used with all CNN models. In our experiments, we demonstrate how the performance of a convolutional feature extractor can be preliminarily evaluated using NAM. We also present results obtained for a simple NAM-based visual attention mechanism, which allows us to filter out less informative regions of the image and facilitates the decision making process.
{"title":"NAM: What Does a Neural Network See?","authors":"Katarzyna Filus, J. Domańska","doi":"10.1109/IJCNN55064.2022.9892442","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892442","url":null,"abstract":"Deep Convolutional Neural Networks (CNNs) still lack interpretability and are often treated as miraculous blackbox machines. Therefore, when an intelligent system fails, it is usually difficult to troubleshoot the problems. Among others, these issues can be caused by incorrect decisions of the CNN classifier. The other reason can be selective “blindness” of the CNN - caused by an insufficient generalization of the convolutional feature extractor. To better understand the CNN decisions, methods from the Class Activation Mapping (CAM) family have been introduced. In contrast to CAM techniques, which focus on the model's predictions (thus a classifier), we propose a simple yet informative way to visualize network activation - Network Activation Mapping (NAM). Our method targets the most important part of the CNN - a convolutional feature extractor. Opposed to CAM methods, NAM is class-and classifier-independent and provides insight into what the neural network focuses on during the feature extraction process and what features it finds the most prominent in the examined image. Due to the classifier-independence, it can be used with all CNN models. In our experiments, we demonstrate how the performance of a convolutional feature extractor can be preliminarily evaluated using NAM. We also present results obtained for a simple NAM-based visual attention mechanism, which allows us to filter out less informative regions of the image and facilitates the decision making process.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116658823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892772
Diego Stucchi, Luca Frittoli, G. Boracchi
We introduce Class Distribution Monitoring (CDM), an effective concept-drift detection scheme that monitors the class-conditional distributions of a datastream. In particular, our solution leverages multiple instances of an online and nonparametric change-detection algorithm based on QuantTree. CDM reports a concept drift after detecting a distribution change in any class, thus identifying which classes are affected by the concept drift. This can be precious information for diagnostics and adaptation. Our experiments on synthetic and real-world datastreams show that when the concept drift affects a few classes, CDM outperforms algorithms monitoring the overall data distribution, while achieving similar detection delays when the drift affects all the classes. Moreover, CDM outperforms comparable approaches that monitor the classification error, particularly when the change is not very apparent. Finally, we demonstrate that CDM inherits the properties of the underlying change detector, yielding an effective control over the expected time before a false alarm, or Average Run Length (ARL0).
{"title":"Class Distribution Monitoring for Concept Drift Detection","authors":"Diego Stucchi, Luca Frittoli, G. Boracchi","doi":"10.1109/IJCNN55064.2022.9892772","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892772","url":null,"abstract":"We introduce Class Distribution Monitoring (CDM), an effective concept-drift detection scheme that monitors the class-conditional distributions of a datastream. In particular, our solution leverages multiple instances of an online and nonparametric change-detection algorithm based on QuantTree. CDM reports a concept drift after detecting a distribution change in any class, thus identifying which classes are affected by the concept drift. This can be precious information for diagnostics and adaptation. Our experiments on synthetic and real-world datastreams show that when the concept drift affects a few classes, CDM outperforms algorithms monitoring the overall data distribution, while achieving similar detection delays when the drift affects all the classes. Moreover, CDM outperforms comparable approaches that monitor the classification error, particularly when the change is not very apparent. Finally, we demonstrate that CDM inherits the properties of the underlying change detector, yielding an effective control over the expected time before a false alarm, or Average Run Length (ARL0).","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120856232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892971
S. Talebi, Stefan Werner, D. Mandic
From the inaugural steps of McCulloch and Pitts to put forth a composition for an electrical brain, that combined with the conception of an adaptive leaning mechanism by Widrow and Hoff has given rise to the phenomena of intelligent machines, machine learning techniques have gained the status of a miracle solution in a myriad of scientific fields. At the heart of these techniques lies iterative optimisation processes that are derived based on first, and in some cases, second-order derivatives. This manuscript, however, aims to expand the mentioned framework to that of using fractional-order derivatives. The entire format of adaptation is revised form the perspective of fractional-order calculus and the appropriate framework for taking full advantage of the fractional-order calculus in learning and adaptation paradigms is formulated. For rigour, the structure of behavioural analysis and performance prediction of this novel class of learning machines is also forged.
{"title":"Fractional-Order Learning Systems","authors":"S. Talebi, Stefan Werner, D. Mandic","doi":"10.1109/IJCNN55064.2022.9892971","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892971","url":null,"abstract":"From the inaugural steps of McCulloch and Pitts to put forth a composition for an electrical brain, that combined with the conception of an adaptive leaning mechanism by Widrow and Hoff has given rise to the phenomena of intelligent machines, machine learning techniques have gained the status of a miracle solution in a myriad of scientific fields. At the heart of these techniques lies iterative optimisation processes that are derived based on first, and in some cases, second-order derivatives. This manuscript, however, aims to expand the mentioned framework to that of using fractional-order derivatives. The entire format of adaptation is revised form the perspective of fractional-order calculus and the appropriate framework for taking full advantage of the fractional-order calculus in learning and adaptation paradigms is formulated. For rigour, the structure of behavioural analysis and performance prediction of this novel class of learning machines is also forged.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120878411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892075
R. Lin, Lianglun Cheng, Tao Wang, Jianfeng Deng
Taking fault diagnosis corpus as the research object, an event logic knowledge graph construction method is proposed in this paper. Firstly, we propose a data labeling strategy based on a constructed event logic ontology model, then collect large-scale robot transmission system fault diagnosis corpus, and label part of the data according to the strategy. Secondly, we propose a transfer learning model called Trans-SBLGCN for event argument entity and event argument relation joint extraction. A language model is trained based on large-scale unlabeled fault diagnosis corpus and transferred to a model based on stacked bidirectional long short term memory (BiLSTM) and bidirectional graph convolutional network (BiGCN). Experimental results show that the method is superior to other methods. Finally, an event logic knowledge graph of robot transmission system fault diagnosis is constructed to provide decision support for autonomous robot transmission system fault diagnosis.
{"title":"Trans-SBLGCN: A Transfer Learning Model for Event Logic Knowledge Graph Construction of Fault Diagnosis","authors":"R. Lin, Lianglun Cheng, Tao Wang, Jianfeng Deng","doi":"10.1109/IJCNN55064.2022.9892075","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892075","url":null,"abstract":"Taking fault diagnosis corpus as the research object, an event logic knowledge graph construction method is proposed in this paper. Firstly, we propose a data labeling strategy based on a constructed event logic ontology model, then collect large-scale robot transmission system fault diagnosis corpus, and label part of the data according to the strategy. Secondly, we propose a transfer learning model called Trans-SBLGCN for event argument entity and event argument relation joint extraction. A language model is trained based on large-scale unlabeled fault diagnosis corpus and transferred to a model based on stacked bidirectional long short term memory (BiLSTM) and bidirectional graph convolutional network (BiGCN). Experimental results show that the method is superior to other methods. Finally, an event logic knowledge graph of robot transmission system fault diagnosis is constructed to provide decision support for autonomous robot transmission system fault diagnosis.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120930424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Memes are spreading on social networking. Most are created to be humorous, while some become hateful with the combination of images and words, conveying negative information to people. The hateful memes detection poses an interesting multimodal fusion problem, unlike traditional multi-modal tasks, the majority of memos have images and text that are only weakly consistent or even uncorrelated, so various modalities contained in the data play an important role in predicting its results. In this paper, we attempt to work on the Facebook Meme challenge, which solves the binary classification task of predicting a meme's hatefulness or not. We extract triplet-relation information from origin OCR text features, image content features and image caption features and proposed a novel cross-attention network to address this task. TRICAN leverages object detection and image caption models to explore visual modalities to obtain “actual captions” and then combines combine origin OCR text with the multi-modal representation to perform hateful memes detection. These meme-related features are then reconstructed and fused into one feature vector for prediction. We have performed extensively experimental on multi-modal memory datasets. Experimental results demonstrate the effectiveness of TRICAN and the usefulness of triplet-relation information.
{"title":"TRICAN: Multi-Modal Hateful Memes Detection with Triplet-Relation Information Cross-Attention Network","authors":"Xiaolin Liang, Yajuan Huang, Wen Liu, He Zhu, Zhao Liang, Libo Chen","doi":"10.1109/IJCNN55064.2022.9892164","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892164","url":null,"abstract":"Memes are spreading on social networking. Most are created to be humorous, while some become hateful with the combination of images and words, conveying negative information to people. The hateful memes detection poses an interesting multimodal fusion problem, unlike traditional multi-modal tasks, the majority of memos have images and text that are only weakly consistent or even uncorrelated, so various modalities contained in the data play an important role in predicting its results. In this paper, we attempt to work on the Facebook Meme challenge, which solves the binary classification task of predicting a meme's hatefulness or not. We extract triplet-relation information from origin OCR text features, image content features and image caption features and proposed a novel cross-attention network to address this task. TRICAN leverages object detection and image caption models to explore visual modalities to obtain “actual captions” and then combines combine origin OCR text with the multi-modal representation to perform hateful memes detection. These meme-related features are then reconstructed and fused into one feature vector for prediction. We have performed extensively experimental on multi-modal memory datasets. Experimental results demonstrate the effectiveness of TRICAN and the usefulness of triplet-relation information.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120986433","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892525
Lucas Candeia Teixeira, Júlio César Gomes De Barros, Bruno José Torres Fernandes, Carlo Marcelo Revoredo da Silva
The growth in the numbers of phishing attacks, along with the volume of successful frauds, demonstrates vul-nerabilities of the protection tools and exposes the advance in the refinement of the attacks. In more than 70% of cases, the improvements rely on the presence of homographic terms as a mechanism to embed reliability in malicious pages. In this scenario, the present study proposes an intelligent approach denominated CatchPhish, which, through the attack target brand identification, can infer the veracity of the page evaluated. CatchPhish uses a Siamese neural network capable of identifying the presence of typosquatting mentions in phishing pages. In the experiments, the proposed approach achieved 99.30% of assertiveness. In addition, the proposed approach stands out for its ability to produce terms for training, so, instead of providing the tool with a high amount of distorted terms, it provides the mark preceded by the correct spelling, which circumvents a strong obstacle in the construction of protection mechanisms.
{"title":"CatchPhish: Model for detecting homographic attacks on phishing pages","authors":"Lucas Candeia Teixeira, Júlio César Gomes De Barros, Bruno José Torres Fernandes, Carlo Marcelo Revoredo da Silva","doi":"10.1109/IJCNN55064.2022.9892525","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892525","url":null,"abstract":"The growth in the numbers of phishing attacks, along with the volume of successful frauds, demonstrates vul-nerabilities of the protection tools and exposes the advance in the refinement of the attacks. In more than 70% of cases, the improvements rely on the presence of homographic terms as a mechanism to embed reliability in malicious pages. In this scenario, the present study proposes an intelligent approach denominated CatchPhish, which, through the attack target brand identification, can infer the veracity of the page evaluated. CatchPhish uses a Siamese neural network capable of identifying the presence of typosquatting mentions in phishing pages. In the experiments, the proposed approach achieved 99.30% of assertiveness. In addition, the proposed approach stands out for its ability to produce terms for training, so, instead of providing the tool with a high amount of distorted terms, it provides the mark preceded by the correct spelling, which circumvents a strong obstacle in the construction of protection mechanisms.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127107585","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892790
Zhengkai Wang, Weiyu Zhang, Zhongxiu Xia, Wenpeng Lu
COVID-19 has become a worldwide epidemic. Prediction of COVID-19 is an effective way to control its spread. Recently, some research efforts have made great progress on this task. However, these works rarely combine both the temporal and spatial domains for case number prediction. Moreover, most of them are only suitable for short-term prediction tasks, which cannot achieve good long-term predicting effects. Therefore, we use a method that combines human-mobility factors and time-series factors - the Spatio-temporal convolutional network (G-TCN) to deal with these problems. Firstly, we use data on the mobility of people between regions to generate graphs of regional relationships. Secondly, to process the spatial information at each moment, we apply multi-layer graph convolutional neural networks (GCNs) to aggregate multi-layer neighborhood information. And we input the information obtained by GCNs at different moments into temporal convolutional networks (TCNs), which are used to process the time-series information. Finally, we tested the proposed G-TCN method using datasets from four countries. The experimental results show that G-TCN has lower prediction errors than other comparison methods and can better fit the trend of COVID-19 development.
{"title":"A Model for COVID-19 Prediction Based on Spatio-temporal Convolutional Network","authors":"Zhengkai Wang, Weiyu Zhang, Zhongxiu Xia, Wenpeng Lu","doi":"10.1109/IJCNN55064.2022.9892790","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892790","url":null,"abstract":"COVID-19 has become a worldwide epidemic. Prediction of COVID-19 is an effective way to control its spread. Recently, some research efforts have made great progress on this task. However, these works rarely combine both the temporal and spatial domains for case number prediction. Moreover, most of them are only suitable for short-term prediction tasks, which cannot achieve good long-term predicting effects. Therefore, we use a method that combines human-mobility factors and time-series factors - the Spatio-temporal convolutional network (G-TCN) to deal with these problems. Firstly, we use data on the mobility of people between regions to generate graphs of regional relationships. Secondly, to process the spatial information at each moment, we apply multi-layer graph convolutional neural networks (GCNs) to aggregate multi-layer neighborhood information. And we input the information obtained by GCNs at different moments into temporal convolutional networks (TCNs), which are used to process the time-series information. Finally, we tested the proposed G-TCN method using datasets from four countries. The experimental results show that G-TCN has lower prediction errors than other comparison methods and can better fit the trend of COVID-19 development.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127128545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：