With the increasing development of deep learning models, the security of these models has become more important. In this work, for the first time, we have investigated the possibility of abusing the deep model as a covert channel. The concept of a covert channel is to use a channel that is not designed for information exchange for transmitting a covert message. This work studies how a deep model can be used by an adversary as a covert channel. The proposed approach is using an end-to-end training deep model called the covert model to produce artificial data which includes some covert messages. This artificial data is the input of the deep model, which is aimed at being exploited as a covert channel, in such a way that the signal will be covered in the output of this model. To achieve indistinguishability of concealment, generative adversarial networks are used. The results show that it is possible to have a covert channel with an acceptable message transmission power in well-known deep models such as the ResNet and InceptionV3 models. Results of case studies indicate the signal-to-noise ratio (SNR) of 12.67, the bit error rate (BER) of 0.08, and the accuracy of the deep model used to hide the signal reaches 92%.

Despite the impressive success of sequence to sequence models for generative question answering, they need a vast amount of question-answer pairs during training, which is hard and expensive to obtain, especially for low-resource languages. In this article, we present a framework that exploits the semantic clusters among the question-answer pairs to compensate for the lack of enough training data. In the training phase, the question-answer pairs are clustered, and a cluster predictor is trained to identify the cluster each question belongs to. Then, a sequence to sequence model is trained, where there is a different generator for each cluster in the decoder component. During the test phase, the cluster of the input question is first identified using the trained cluster predictor, and the appropriate decoder is exploited. Our experiments on a Persian religious dataset show that the proposed method outperforms the standard sequence to sequence model by a large margin in terms of ROUGE and BLEU scores. This is traced back to the lower number of words in each cluster, leading to a reduction in the number of effective parameters each generator needs to learn, which help the model learn from fewer training data with less overfitting.

Abstract When a user connects to the Internet to fulfill his needs, he often encounters a huge amount of related information. Recommender systems are the techniques for massively filtering information and offering the items that users find them satisfying and interesting. The advances in machine learning methods, especially deep learning, have led to great achievements in recommender systems, although these systems still suffer from challenges such as cold‐start and sparsity problems. To solve these problems, context information such as user communication network is usually used. In this article, we have proposed a novel recommendation method based on matrix factorization and graph analysis methods, namely Louvain for community detection and HITS for finding the most important node within the trust network. In addition, we leverage deep autoencoders to initialize users and items latent factors, and the Node2vec deep embedding method gathers users' latent factors from the user trust graph. The proposed method is implemented on Ciao and Epinions standard datasets. The experimental results and comparisons demonstrate that the proposed approach is superior to the existing state‐of‐the‐art recommendation methods. Our approach outperforms other comparative methods and achieves great improvements, that is, 15.56% RMSE improvement for Epinions and 18.41% RMSE improvement for Ciao.

Abstract The development of knowledge sharing platforms, like scientific social networks encourages researchers to establish international collaboration in scientific projects. After reviewing the previous methods for collaborator detection in social networks, gaps in the earlier models are investigated, and the present study aims at filling the gaps by introducing a new scientific collaborator recommendation system. Accordingly, in the present paper, an integrated model is presented based on multilayer networks that can personalize the proposing scientific collaborators. Our proposed model involves various types of collaboration features based on researchers' needs. In our method a scientific social network is modelled as a multi‐relational network (MRN), in which collaborators are determined by a community detection algorithm. It provides us with an approach to integrate the personalized features into the collaborator detection model that is due to the essence of semi‐supervisory learning of our community detection algorithm. This MRN helps us prevent information loss in the network. We considered two techniques for examining the models. The first one was General Collaborator Recommendation, and the second one was a Collaborator with Personalization Ability. The proposed method is applied to the data of the ResearchGate (RG) social network and is evaluated by criteria, such as F index and NMI.

Abstract The increasing trend of smartphone capabilities has caught the attention of many users. This has led to the emergence of malware that threatening the users' privacy and security. Many malware detection methods have been proposed to deal with emerging threats. One of the most effective ones is to use network traffic analysis. This article proposed a method based on LSTM (Long Short‐term Memory) for malware detection which is capable of not only distinguishing malware and benign samples, but also detecting and identify the new and unseen families of malware. As far as we know, this is the first time that traffic data has been modeled as a sequence of flows and a sequential based deep learning model is employed. In this article, we have performed several case studies to exhibit the capabilities of the proposed method including malware detection, malware family identification, new (not seen before) malware family detection, as well as evaluating the minimum time required to detect malware. The case studies show that the model is even capable of detecting new families of malware with more than 90% accuracy, although these results can only be verified on existing families in this dataset and such a claim cannot be generalized to other examples of malware. Moreover, it is shown the model is able to detect the malware through capturing 50 connection flows (about 1600 packets in average) with the AUC of more than 99.9%.

Nowadays, trust systems (TSs) are widely used for tackling dishonest entities in many modern environments. However, these systems are vulnerable to some kinds of attacks where attackers try to deceive the system using sequences of misleading behaviors and dishonest recommendations. A robust TS is expected to function properly even in the possibility of such attacks. To the best of our knowledge, simulation has been the main approach for evaluation of TSs so far, and there is no remarkable verification method for this aim. In this paper, a method for quantitative verification of TSs' robustness against malicious attackers is proposed. The proposed method consists of a formalism for specifying any given trust model named TS attack process that is cast into partially observable Markov decision process mathematical framework. The proposed method is capable of verifying TSs against both well-known attacks and the worst possible attack scenario. The method could also be used to help adjusting parameters of the given TS. Moreover, a quantitative robustness measure is introduced, which helps to compare the robustness of different TSs. To illustrate the applicability of the proposed method, a number of case studies for analysis and comparison of selected trust models (including Subjective Logic and REGRET) are presented.