Network traffic classification serves as a building block for important tasks such as security and quality of service management. The field has been studied for a long time, with many techniques such as classical machine learning and deep learning methods currently available. However, the emergence of stronger encryption protocols has led to the rise of new challenges. One of the challenges is capturing and labeling a large amount of encrypted traffic data especially for training deep learning classifiers, as current techniques rely on deep packet inspection tools (DPI) which perform poorly on encrypted traffic. In this paper, we propose a semi-supervised learning approach using Deep Convolutional Generative Adversarial Network (DCGAN). The basic idea is to utilize the samples generated by DCGAN generators as well as unlabeled data to improve the performance of a classifier trained on a few labeled samples. Thus, alleviating the difficulties associated with large dataset collecting and labeling. To demonstrate the efficacy of our approach, we evaluated our model using a self-collected dataset of the recently established QUIC protocol as well as publicly available ISCX VPN-NonVPN dataset. Our approach is able to achieve 89% and 78% accuracy with a very small number of labeled samples (just 10% of the dataset) on both QUIC and ISCX VPN-NonVPN datasets respectively.
5 March 2022 in International Journal of Information Technology
Sentence simplification is an essential task in natural language processing and aims to simplify complex sentences while retaining their primary meanings. To date, the main research works on sentence simplification models have been based on sequence‐to‐sequence (Seq2Seq) models. However, these Seq2Seq models are incapable of analysing the hierarchical structure of sentences, which is of great significance for sentence simplification. The problem can be addressed with an ON‐MULTI‐STAGE model constructed based on the improved MULTI‐STAGE encoder model. In this model, an ordered neurons network is introduced and can provide sentence‐level structural information for the encoder and decoder. A weak attention connection method is then employed to make the decoder use the sentence‐level structural details. Experimental results on two open data sets demonstrated that the constructed model outperforms the state‐of‐the‐art baseline models in sentence simplification.
Information sharing through online social networks has become a main mechanism by which people share information with their friends through retweeting behaviors, which may result in a variety of information diffusion cascades on social media such as Facebook, Twitter, and Weibo. Predicting user retweeting behavior in those social networks is extremely challenging. To complete the prediction task, identifying factors that affect retweeting behavior and constructing efficient model are necessary. In this paper, we study heterogeneous relation networks by considering various social interactions, which reflect how a particular retweeting action is affected by the social behaviors performed by the sender and the receiver of the retweet. We then generate various features from our identified factors belonging to three dimensions – content semantics, user diffusion behavior, and network structure. Moreover, we cast our prediction problem as an ensemble learning problem and propose a novel ensemble learning approach to solve the problem. Combing the generated features and the novel ensemble learning approach, we then propose a model named Retweeting Behavior on Multiple Heterogeneous Diffusion Relation Networks (RBMHDRN) to predict user retweeting behavior in social networks. Experiments on a real dataset extracted from a social network site Weibo demonstrate the effectiveness of our proposed model, indicating that our generated features and proposed approach can significantly improve the performance of predicting user retweeting behavior occurring in the process of information diffusion in social networks.
2 November 2020 in CAAI Transactions on Intelligence Technology
Part‐of‐speech (POS) and dependency grammar (DG) are the basic components of natural language processing. However, current word vector models have not made full use of both POS information and DG information, and hence the models’ performances are limited to some extent. The authors first put forward the concept of POS vector, and then, based on continuous bag‐of‐words (CBOW), constructed four models: CBOW + P, CBOW + PW, CBOW + G, and CBOW + G + P to incorporate POS information and DG information into word vectors. The CBOW + P and CBOW + PW models are based on POS tagging, the CBOW + G model is based on DG parsing, and the CBOW + G + P model is based on POS tagging and DG parsing. POS information is integrated into the training process of word vectors through the POS vector to solve the problem of the POS similarity being difficult to measure. The POS vector correlation coefficient and distance weighting function are used to train the POS vector as well as the word vector. DG information is used to correct the information loss caused by fixed context windows. Dependency relations weight is used to measure the difference of dependency relations. Experiments demonstrated the superior performance of their models while the time complexity is still kept the same as the base model of CBOW.
Voice Conversion (VC) is a method of converting the source speaker’s speech into the target speaker’s speech without changing the source speaker’s speech content. The current VC methods have the following problems: (1) they are only applicable to a limited number of speakers, not to any speakers, as a result, the application scenarios are greatly restricted; (2) the representation (feature) separation(RS) effect of the current mainstream technology is not ideal on the source speaker speech and the target speaker speech; and (3) the voice conversion quality of most models is unsatisfactory, and hence needs to be improved. Therefore, in this paper, we constructed a one-shot VC model of Representation Separation, called RS-VC model, implemented by the encoder-decoder structure. The encoder is composed of a content encoder and a speaker encoder. The content encoder separates the content information of the source speaker voice and generates a content representation. The speaker encoder separates the target speaker information of the target speaker voice and generates a speaker representation. The decoder synthesizes the content representation and the speaker representation to generate the converted voice. In this paper, we obtained the optimized speaker verification model SVIGEN2E (Speaker Verification with Instance Normalization using Generalized End-to-End loss) by improving the speaker verification (SV) model. The model SVIGEN2E is used as the speaker encoder. This speaker encoder needs to be trained in advance prior to RS-VC model training, and the pre-trained model of SVINGE2E directly extracts speaker representation of the target speaker’s voice, and is used for training and testing RS-VC model. A progressive training method is proposed then for training RS-VC model. Experiments show that the progressive training method can effectively improve the quality of the converted voice. Compared with the basic speaker verification model, both SVINGE2E and RS-VC deliver the impressive improvements in EER (Equal Error Rate).