Biblio

A recommender system aims to suggest the most relevant items to users based on their personal data. However, data privacy is a growing concern for anyone. Secure recommender system is a research direction to preserve user privacy while maintaining as high performance as possible. The most recent strategy is to use Federated Learning, a machine learning technique for privacy-preserving distributed training. In Federated Learning, a subset of users will be selected for training model using data at local systems, the server will securely aggregate the computing result from local models to generate a global model, finally that model will give recommendations to users. In this paper, we present a novel algorithm to train Collaborative Filtering recommender system specialized for the ranking task in Federated Learning setting, where the goal is to protect user interaction information (i.e., implicit feedback). Specifically, with the help of the algorithm, the recommender system will be trained by Neural Collaborative Filtering, one of the state-of-the-art matrix factorization methods and Bayesian Personalized Ranking, the most common pairwise approach. In contrast to existing approaches which protect user privacy by requiring users to download/upload the information associated with all interactions that they can possibly interact with in order to perform training, the algorithm can protect user privacy at low communication cost, where users only need to obtain/transfer the information related to a small number of interactions per training iteration. Above all, through extensive experiments, the algorithm has demonstrated to utilize user data more efficient than the most recent research called FedeRank, while ensuring that user privacy is still preserved.

A recommender system is a filtering application based on personalized information from acquired big data to predict a user's preference. Traditional recommender systems primarily rely on keywords or scene patterns. Users' subjective emotion data are rarely utilized for preference prediction. Novel Brain Computer Interfaces hold incredible promise and potential for intelligent applications that rely on collected user data like a recommender system. This paper describes a deep learning method that uses Brain Computer Interfaces (BCI) based neural measures to predict a user's preference on short music videos. Our models are employed on both population-wide and individualized preference predictions. The recognition method is based on dynamic histogram measurement and deep neural network for distinctive feature extraction and improved classification. Our models achieve 97.21%, 94.72%, 94.86%, and 96.34% classification accuracy on two-class, three-class, four-class, and nine-class individualized predictions. The findings provide evidence that a personalized recommender system on an implicit BCI has the potential to succeed.

Recommender systems have been proved to be effective techniques to provide users with better experiences. However, when a recommender knows the user's preference characteristics or gets their sensitive information, then a series of privacy concerns are raised. A amount of solutions in the literature have been proposed to enhance privacy protection degree of recommender systems. Although the existing solutions have enhanced the protection, they led to a decrease in recommendation accuracy simultaneously. In this paper, we propose a security-aware hybrid recommendation method by combining the factorization and regression techniques. Specifically, the differential privacy mechanism is integrated into data pre-processing for data encryption. Firstly data are perturbed to satisfy differential privacy and transported to the recommender. Then the recommender calculates the aggregated data. However, applying differential privacy raises utility issues of low recommendation accuracy, meanwhile the use of a single model may cause overfitting. In order to tackle this challenge, we adopt a fusion prediction model by combining linear regression (LR) and matrix factorization (MF) for collaborative recommendation. With the MovieLens dataset, we evaluate the recommendation accuracy and regression of our recommender system and demonstrate that our system performs better than the existing recommender system under privacy requirement.

In the economics environment, Job Matching is always a challenge involving the evolution of knowledge and skills. A good matching of skills and jobs can stimulate the growth of economics. Recommender System (RecSys), as one kind of Job Matching, can help the candidates predict the future job relevant to their preferences. However, RecSys still has the problem of cold start and data sparsity. The content-based filtering in RecSys needs the adaptive data for the specific staffing tasks of Bidirectional Encoder Representations from Transformers (BERT). In this paper, we propose a job RecSys based on skills and locations using a domain-specific Knowledge Graph (KG). This system has three parts: a pipeline of Named Entity Recognition (NER) and Relation Extraction (RE) using BERT; a standardization system for pre-processing, semantic enrichment and semantic similarity measurement; a domain-specific Knowledge Graph (KG). Two different relations in the KG are computed by cosine similarity and Term Frequency-Inverse Document Frequency (TF-IDF) respectively. The raw data used in the staffing RecSys include 3000 descriptions of job offers from Indeed, 126 Curriculum Vitae (CV) in English from Kaggle and 106 CV in French from Linx of Capgemini Engineering. The staffing RecSys is integrated under an architecture of Microservices. The autonomy and effectiveness of the staffing RecSys are verified through the experiment using Discounted Cumulative Gain (DCG). Finally, we propose several potential research directions for this research.

In the last few years, cluster ensembles have emerged as powerful techniques that integrate multiple clustering methods into recommender systems. Such integration leads to improving the performance, quality and the accuracy of the generated recommendations. This paper proposes a novel recommender system based on a cluster ensemble technique for big data. The proposed system incorporates the collaborative filtering recommendation technique and the cluster ensemble to improve the system performance. Besides, it integrates the Expectation-Maximization method and the HyperGraph Partitioning Algorithm to generate new recommendations and enhance the overall accuracy. We use two real-world datasets to evaluate our system: TED Talks and MovieLens. The experimental results show that the proposed system outperforms the traditional methods that utilize single clustering techniques in terms of recommendation quality and predictive accuracy. Most importantly, the results indicate that the proposed system provides the highest precision, recall, accuracy, F1, and the lowest Root Mean Square Error regardless of the used similarity strategy.

Cloud computing is applied in various domains, among which social recommender systems are well-received because of their effectivity to provide suggestions for users. Social recommender systems perform well in alleviating cold start problem, but it suffers from shilling attack due to its natural openness. Shilling attack is an injection attack mainly acting on the training process of machine learning, which aims to advance or suppress the recommendation ranking of target items. Some researchers have studied the influence of shilling attacks in two perspectives simultaneously, which are user-item's rating and user-user's relation. However, they take more consideration into user-item's rating, and up to now, the construction of user-user's relation has not been explored in depth. To explore shilling attacks with complex relations, in this paper, we propose two novel attack models based on triangle relations in social networks. Furthermore, we explore the influence of these models on five social recommendation algorithms. The experimental results on three datasets show that the recommendation can be affected by the triangle relation attacks. The attack model combined with triangle relation has a better attack effect than the model only based on rating injection and the model combined with random relation. Besides, we compare the functions of triangle relations in friend recommendation and product recommendation.

Recent advances in information filtering have resulted in effective recommender systems that are able to provide online personalized recommendations to millions of users from all over the world. However, most of these systems ignore the explanation purpose while producing recommendations with high-quality results. Moreover, the classification of reviews given to users as explanations is not fully exploited in previous studies. In this paper, we develop a convolutional neural network-based reviews classification method for explainable recommendation systems. The convolutional neural network is used to extract the reviews features for predicting whether the reviews provided as explanations are positive or negative. Based on such additional information, users can understand not only why certain items are recommended for them but also get support to know the nature of such explanations. We conduct experiments on a dataset from Amazon. The experimental results show that our method outperforms state-of-the-art methods.

The recommender system is an important application in big data analytics because accurate recommendation items or high-valued suggestions can bring high profit to both commercial companies and customers. To make precise recommendations, a recommender system often needs large and fine-grained data for training. In the current big data era, data often exist in the form of isolated islands, and it is difficult to integrate the data scattered due to privacy security concerns. Moreover, privacy laws and regulations make it harder to share data. Therefore, designing a privacy-preserving recommender system is of paramount importance. Existing privacy-preserving recommender system models mainly adapt cryptography approaches to achieve privacy preservation. However, cryptography approaches have heavy overhead when performing encryption and decryption operations and they lack a good level of flexibility. In this paper, we propose a Locality Sensitive Hashing (LSH) based approach for federated recommender system. Our proposed efficient and scalable federated recommender system can make full use of multiple source data from different data owners while guaranteeing preservation of privacy of contributing parties. Extensive experiments on real-world benchmark datasets show that our approach can achieve both high time efficiency and accuracy under small privacy budgets.

Collaborative Filtering (CF) is a popular recommendation system that makes recommendations based on similar users' preferences. Though it is widely used, CF is prone to Shilling/Profile Injection attacks, where fake profiles are injected into the CF system to alter its outcome. Most of the existing shilling attacks do not work on online systems and cannot be efficiently implemented in real-world applications. In this paper, we introduce an efficient Multi-Armed-Bandit-based reinforcement learning method to practically execute online shilling attacks. Our method works by reducing the uncertainty associated with the item selection process and finds the most optimal items to enhance attack reach. Such practical online attacks open new avenues for research in building more robust recommender systems. We treat the recommender system as a black box, making our method effective irrespective of the type of CF used. Finally, we also experimentally test our approach against popular state-of-the-art shilling attacks.

The pervasiveness of personalized collaborative recommender systems has shown the powerful capability in a wide range of E-commerce services such as Amazon, TripAdvisor, Yelp, etc. However, fundamental vulnerabilities of collaborative recommender systems leave space for malicious users to affect the recommendation results as the attackers desire. A vast majority of existing detection methods assume certain properties of malicious attacks are given in advance. In reality, improving the detection performance is usually constrained due to the challenging issues: (a) various types of malicious attacks coexist, (b) limited representations of malicious attack behaviors, and (c) practical evidences for exploring and spotting anomalies on real-world data are scarce. In this paper, we investigate a unified detection framework in an eye for an eye manner without being bothered by the details of the attacks. Firstly, co-visitation and co-rating graphs are constructed using association rules. Then, attribute representations of nodes are empirically developed from the perspectives of linkage pattern, structure-based property and inherent association of nodes. Finally, both attribute information and connective coherence of graph are combined in order to infer suspicious nodes. Extensive experiments on both synthetic and real-world data demonstrate the effectiveness of the proposed detection approach compared with competing benchmarks. Additionally, abnormality forensics metrics including distribution of rating intention, time aggregation of suspicious ratings, degree distributions before as well as after removing suspicious nodes and time series analysis of historical ratings, are provided so as to discover interesting findings such as suspicious nodes (items or ratings) on real-world data.

Matrix factorization (MF) has been proved to be an effective approach to build a successful recommender system. However, most current MF-based recommenders cannot obtain high prediction accuracy due to the sparseness of user-item matrix. Moreover, these methods suffer from the scalability issues when applying on large-scale real-world tasks. To tackle these issues, in this paper a social regularization method called TrustRSNMF is proposed that incorporates the social trust information of users in nonnegative matrix factorization framework. The proposed method integrates trust statements along with user-item ratings as an additional information source into the recommendation model to deal with the data sparsity and cold-start issues. In order to evaluate the effectiveness of the proposed method, a number of experiments are performed on two real-world datasets. The obtained results demonstrate significant improvements of the proposed method compared to state-of-the-art recommendation methods.

The security of user personal information on cloud computing is an important issue for the recommendation system. In order to provide high quality recommendation services, privacy of user is often obtained by untrusted recommendation systems. At the same time, malicious attacks often use the recommendation results to try to guess the private data of user. This paper proposes a hybrid algorithm based on NMF and random perturbation technology, which implements the recommendation system and solves the protection problem of user privacy data in the recommendation process on cloud computing. Compared with the privacy protection algorithm of SVD, the elements of the matrix after the decomposition of the new algorithm are non-negative elements, avoiding the meaninglessness of negative numbers in the matrix formed by texts, images, etc., and it has a good explanation for the local characteristics of things. Experiments show that the new algorithm can produce recommendation results with certain accuracy under the premise of protecting users' personal privacy on cloud computing.

New software vulnerabilities are published daily. Prioritizing vulnerabilities according to their relevance to the collection of software an organization uses is a costly and slow process. While recommender systems were earlier proposed to address this issue, they ignore the security of the vulnerability prioritization data. As a result, a malicious operator or a third party adversary can collect vulnerability prioritization data to identify the security assets in the enterprise deployments of client organizations. To address this, we propose a solution that leverages isolated execution to protect the privacy of vulnerability profiles without compromising data integrity. To validate an implementation of the proposed solution we integrated it with an existing recommender system for software vulnerabilities. The evaluation of our implementation shows that the proposed solution can effectively complement existing recommender systems for software vulnerabilities.

The condition of road surface has a significant role in land transportation. Due to poor road conditions, the logistics and supply chain industry face a drastic loss in their business. Unmaintained roads can cause damage to goods and accidents. The existing routing techniques do not consider factors like shock, temperature and tilt of goods etc. but these factors have to be considered for the logistics and supply chain industry. This paper proposes a recommender system which target management of goods in logistics. A 3 axis accelerometer is used to measure the road surface conditions. The pothole location is obtained using Global Positioning System (GPS). Using these details a hybrid recommender system is built. Hybrid recommender system combines multiple recommendation techniques to develop an effective recommender system. Here content-based and collaborative-based techniques is combined to build a hybrid recommender system. One of the popular Multiple Criteria Decision Making (MCDM) method, The Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) is used for content based filtering and normalised Euclidean distance and KNN algorithm is used for collaborative filtering. The best route recommended by the system will be displayed to the user using a map application.

Collaborative filtering (CF) is a successful and hence most widely used technique for recommender systems. However, it is vulnerable to shilling attack due to its open nature, which results in generating biased or false recommendations for users. In literature, segment attack (push attack) has been widely studied and investigated while rare studies have been performed on nuke attack, to the best of our knowledge. Further, the robustness of binary collaborative filtering and hybrid approach has not been investigated against segment-focused attack. In this paper, from the perspective of robustness, binary collaborative filtering, hybrid approach, stand-alone rating user-based, and stand-alone rating item- based recommendation have been evaluated against segment attack on a large dataset (100K ratings) which is found to be more successful as it attacks target set of items. With an aim to find an approach which reflects a higher accuracy in recommending items and is less vulnerable to segment-based attack, the possibility of any relationship between accuracy and vulnerability of six CF approaches were studied. Such an approach needs to be re-examined by the researchers marking the future of recommender system (RS). Experimental results show negligible positive correlation between accuracy and vulnerability of techniques. Publicly available dataset namely MovieLens was used for conducting experiments. Robustness and accuracy of CF techniques were calculated using prediction shift and F-measure, respectively.

Collaborative filtering (CF) recommender system has been widely used for its well performing in personalized recommendation, but CF recommender system is vulnerable to shilling attacks in which shilling attack profiles are injected into the system by attackers to affect recommendations. Design robust recommender system and propose attack detection methods are the main research direction to handle shilling attacks, among which unsupervised PCA is particularly effective in experiment, but if we have no information about the number of shilling attack profiles, the unsupervised PCA will be suffered. In this paper, a new unsupervised detection method which combine PCA and data complexity has been proposed to detect shilling attacks. In the proposed method, PCA is used to select suspected attack profiles, and data complexity is used to pick out the authentic profiles from suspected attack profiles. Compared with the traditional PCA, the proposed method could perform well and there is no need to determine the number of shilling attack profiles in advance.

Machine-Learning-as-a-Service has become increasingly popular, with Recommendation-as-a-Service as one of the representative examples. In such services, providing privacy protection for the users is an important topic. Reviewing privacy-preserving solutions which were proposed in the past decade, privacy and machine learning are often seen as two competing goals at stake. Though improving cryptographic primitives (e.g., secure multi-party computation (SMC) or homomorphic encryption (HE)) or devising sophisticated secure protocols has made a remarkable achievement, but in conjunction with state-of-the-art recommender systems often yields far-from-practical solutions. We tackle this problem from the direction of machine learning. We aim to design crypto-friendly recommendation algorithms, thus to obtain efficient solutions by directly using existing cryptographic tools. In particular, we propose an HE-friendly recommender system, refer to as CryptoRec, which (1) decouples user features from latent feature space, avoiding training the recommendation model on encrypted data; (2) only relies on addition and multiplication operations, making the model straightforwardly compatible with HE schemes. The properties turn recommendation-computations into a simple matrix-multiplication operation. To further improve efficiency, we introduce a sparse-quantization-reuse method which reduces the recommendation-computation time by \$9$\backslash$times\$ (compared to using CryptoRec directly), without compromising the accuracy. We demonstrate the efficiency and accuracy of CryptoRec on three real-world datasets. CryptoRec allows a server to estimate a user's preferences on thousands of items within a few seconds on a single PC, with the user's data homomorphically encrypted, while its prediction accuracy is still competitive with state-of-the-art recommender systems computing over clear data. Our solution enables Recommendation-as-a-Service on large datasets in a nearly real-time (seconds) level.

The global market for intelligent voice-enabled devices is expanding at a fast pace. Comcast, one of the largest cable provides in the US with about 30 million users, has recently reinvented the way that customers can discover and access content on an entertainment platform by introducing a voice remote control for its Xfinity X1 entertainment platform. Spoken language input allows the customer to express what they are interested in on their terms, which has made it significantly more convenient for the users to find their favorite TV channel or movie compared to the traditional limits of a screen menu navigated with the keys of a TV remote. The more natural user experience via voice interface results in voice queries that are considerably more complex to handle compared to channel numbers typed in or movie titles selected on screen and this poses a challenge for the platform to understand the user intent and find the appropriate action for millions of voice queries that we receive every day. This also makes it necessary to adapt the underlying content recommendation algorithms to incorporate the richer intent context from the users. We describe some of the key components of our voice-powered content discovery platform that addresses specifically these issues. We discuss how we leverage multimodal data including voice queries and large database of metadata to enable a more natural search experience via voice queries for finding relevant movies, TV shows or even a specific episode of a series. We describe the models that encode semantic similarities between the content and their metadata to allow users to search for places, people, topics using keywords or phrases that do not explicitly appear in the movie/show titles as is traditionally the case. We describe how this category of voice search queries can be framed as a recommendation problem. Even though voice input is extremely powerful to capture the intent of our customers, the freedom to say anything makes it also more difficult for a voice remote user to know the range of possible queries that are supported by our system. We show how we can leverage millions of voice queries that we receive every day to build and train a deep learning-based recommender system that produces different types of recommendations such as educational suggestions and tips for voice commands that the platform support. Finally, it is important to consider that the true potential of the voice-powered entertainment experience is the result of the fusion of intents expressed in language with navigation of content on the screen via the remote navigation buttons. For all the applications and features discussed in this talk, our recommendation systems are adapted to provide the most relevant suggestions no matter if the voice interface is initiating the action, navigating through the results rendered on the TV screen and narrowing down the set of results by allowing the user to ask follow-up queries or select buttons.

Multi-Objective Recommender Systems (MO-RS) consider several objectives to produce useful recommendations. Besides accuracy, other important quality metrics include novelty and diversity of recommended lists of items. Previous research up to this point focused on naive combinations of objectives. In this paper, we present a new and adaptable strategy for prioritizing objectives focused on users' preferences. Our proposed strategy is based on meta-features, i.e., characteristics of the input data that are influential in the final recommendation. We conducted a series of experiments on three real-world datasets, from which we show that: (i) the use of meta-features leads to the improvement of the Pareto solution set in the search process; (ii) the strategy is effective at making choices according to the specificities of the users' preferences; and (iii) our approach outperforms state-of-the-art methods in MO-RS.

The present age of digital information has presented a heterogeneous online environment which makes it a formidable mission for a noble user to search and locate the required online resources timely. Recommender systems were implemented to rescue this information overload issue. However, majority of recommendation algorithms focused on the accuracy of the recommendations, leaving out other important aspects in the definition of good recommendation such as diversity and serendipity. This results in low coverage, long-tail items often are left out in the recommendations as well. In this paper, we present and explore a recommendation technique that ensures that diversity, accuracy and serendipity are all factored in the recommendations. The proposed algorithm performed comparatively well as compared to other algorithms in literature.

Route planner systems support commuters and city visitors in finding the best route between two arbitrary points. More advanced route planners integrate different transportation modes such as private transport, public transport, car- and bicycle sharing or walking and are able combine these to multi-modal routes. Nevertheless, state-of-the-art planner systems usually do not consider the users' personal preferences or the wisdom of the crowd when suggesting multi-modal routes. Including the knowledge and experience of locals who are familiar with local transport allows identification of alternative routes which are, for example, less crowded during peak hours. Collaborative filtering (CF) is a technique that allows recommending items such as multi-modal routes based on the ratings of users with similar preferences. In this paper, we introduce RouteMe, a mobile recommender system for personalized, multi-modal routes which combines CF with knowledge-based recommendations to increase the quality of route recommendations. We present our hybrid algorithm in detail and show how we integrate it in a working prototype. The results of a user study show that our prototype combining CF, knowledge-based and popular route recommendations outperforms state-of-the-art route planners.

Software engineering is a complex filed with diverse specialties. By the growth of Internet based applications, information security plays an important role in software development process. Finding expert software engineers who have expertise in information security requires too much effort. Stack Overflow is the largest social Q&A Website in the field of software engineering. Stack Overflow contains developers' posts and answers in different software engineering areas including information security. Security related posts are asked in conjunction with various technologies, programming languages, tools and frameworks. In this paper, the content and metadata of Stack Overflow is analysed to find experts in diverse software engineering security related concepts using information security ontology.

Digital Signage (DS) is one of the popular IoT technologies deployed in the urban space. DS can provide wayfinding and urban information to city dwellers and convey targeted messaging and advertising to people approaching the DS. With the rise of the online-to-offline (O2O) mobile commerce, DS also become an important marketing tool in urban retailing. However, most digital signage systems today lack interactive feature and context-aware recommendation engine. Few interactive digital signage systems available today are also insufficient in engaging anonymous viewers and also not considering temporal interaction between viewer and DS system. To overcome the above challenges, this paper proposes a context-aware recommender system framework with novel temporal interaction scheme for IoT based interactive digital signage deployed in urban space to engage anonymous viewer. The results of experiments indicate that the proposed framework improves the advertising effectiveness for DS system deployed in public in urban space.

Preparing recommendations for unknown users or such that correctly respond to the short-term needs of a particular user is one of the fundamental problems for e-commerce. Most of the common Recommender Systems assume that user identification must be explicit. In this paper a Session-Aware Recommender System approach is presented where no straightforward user information is required. The recommendation process is based only on user activity within a single session, defined as a sequence of events. This information is incorporated in the recommendation process by explicit context modeling with factorization methods and a novel approach with Recurrent Neural Network (RNN). Compared to the session modeling approach, RNN directly models the dependency of user observed sequential behavior throughout its recurrent structure. The evaluation discusses the results based on sessions from real-life system with ephemeral items (identified only by the set of their attributes) for the task of top-n best recommendations.