Detecting shilling profiles in collaborative recommender systems via multidimensional profile temporal features

Hao, Yaojun; Zhang, Fuzhi

doi:10.1049/iet-ifs.2017.0012

Cited by 6 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Support Vector Machine (SVM) [12] to get hidden factors from the rating matrix. Usually, timebased detection techniques assume that fake ratings are injected in short intervals of time; [36] use SVM with long duration and decentralized injection attacks information.…”

Section: Related Workmentioning

confidence: 99%

Robust Model-Based Reliability Approach to Tackle Shilling Attacks in Collaborative Filtering Recommender Systems

et al. 2019

View full text Add to dashboard Cite

As the use of recommender systems becomes generalized in society, the interest in varying the orientation of their recommendations is increasing. There are shilling attacks' strategies that introduce malicious profiles in collaborative filtering recommender systems in order to promote the own products or services or to discredit those of the competition. Academic research against shilling attacks has been focused in statistical approaches to detect the unusual patterns in user ratings. Nowadays, there is a growing research area focused on the design of robust machine learning methods to neutralize the malicious profiles inserted into the system. This paper proposes an innovative robust method, based on matrix factorization, to neutralize the shilling attacks. Our method obtains the reliability value associated with each prediction of a user to an item. By monitoring the unusual reliability variations in the items prediction, we can avoid promoting the shilling predictions to the erroneous recommendations. This paper openly provides more than 13 000 individual experiments involving a wide range of attack strategies, both push, and nuke, in order to test the proposed approach. The results show that the proposed method is able to neutralize most of the existing attacks; its performance only decreases in the not relevant situations: when the attack size is not large enough to effectively affect the recommendations provided by the system.

show abstract

Section: Related Workmentioning

confidence: 99%

Robust Model-Based Reliability Approach to Tackle Shilling Attacks in Collaborative Filtering Recommender Systems

et al. 2019

View full text Add to dashboard Cite

show abstract

A state-of-the-art survey on recommendation system and prospective extensions

Patel

2020

Computers and Electronics in Agriculture

View full text Add to dashboard Cite

Role of online media in agriculture development in Vietnam

Nguyen

2020

E3S Web Conf.

View full text Add to dashboard Cite

In the history of Vietnam’s establishment and development, agriculture has always been an important economic sector. In 2019, the agriculture, forestry, and fishery sectors accounted for 13.96% of Vietnam’s GDP. However, this is also the year that witnessed the GDP growth of the agriculture sector plummeted to only 2.2 percent. There are many factors responsible for the decline in the share of agriculture in economic growth, while other sectors have increased. In the current context, with the outstanding development of science and technology, global networking and information society, every aspect of development including agriculture development cannot be separated from the operation of media, especially online media. This paper analyses the role of online media in agriculture development in Vietnam by analyzing hundreds of articles published in different electronic newspapers. The paper particularly examines 217 news-articles produced on VnExpress, the most read Vietnamese newspaper. While discussing the advantages and disadvantages of the role of media in agriculture development, the paper also explores some new paradigm and recommends to enhance the role of online media for digitizing the development of agriculture in Vietnam in this digital age.

show abstract

Detecting shilling profiles in collaborative recommender systems via multidimensional profile temporal features

Cited by 6 publications

References 34 publications

Robust Model-Based Reliability Approach to Tackle Shilling Attacks in Collaborative Filtering Recommender Systems

Robust Model-Based Reliability Approach to Tackle Shilling Attacks in Collaborative Filtering Recommender Systems

A state-of-the-art survey on recommendation system and prospective extensions

Role of online media in agriculture development in Vietnam

Contact Info

Product

Resources

About