Big data recommender systems are very vulnerable to attacks, especially to profile injection attacks. So, we should use security mechanisms to protect big data recommender systems from different kinds of attacks. These vulnerabilities and attacks may decrease users' trust in accuracy of recommender systems. In addition, issues related to big data recommender systems and their security problems are based on security challenges in Hadoop architecture which is called Hadoop Distributed File System (HDFS). In this chapter, we investigate a number of known attack models, examine their influence and suggest some solutions to combat them. Furthermore, we represent different methods that are used by attackers to modify an attack so it is not recognized as an attack. We consider important issues in creating secure big data recommender systems, focusing on attack models and their effect on different big data recommender approaches. We know the general effect on systems' ability to predict accurately, and we also know the amount of knowledge that attackers need to know about the system to deploy a realistic attack. In this chapter, we show that the two approaches, i.e. user-based and item-based algorithms, are particularly vulnerable to attack patterns, but hybrid algorithms that are the combination of both user-based and item-based algorithms may present higher stability. Also, we study the basics of relevant research and advanced schemas, and discuss future thoughts.

Chapter Contents:

• 11.1 Introduction
• 11.2 Security issues and approaches in HDFS architecture
• 11.2.1 Security issues in HDFS
• 11.2.2 HDFS security methods
• 11.2.2.1 Kerberos construction
• 11.2.2.2 Bull Eye algorithm
• 11.2.2.3 Name node algorithm
• 11.3 Big data recommender system attacks
• 11.3.1 Attack tactics
• 11.3.2 Probe attack strategy
• 11.3.3 Ratings strategy
• 11.3.4 Dimensions of attacks
• 11.3.5 Models of attacks
• 11.3.5.1 Profile injection attacks
• 11.3.5.2 Push attacks
• 11.3.5.3 Nuke attacks
• 11.4 Recommender algorithms
• 11.4.1 Association rule mining
• 11.4.2 Base algorithms
• 11.4.3 k-Nearest neighbor
• 11.4.4 k-Means clustering
• 11.4.5 Probabilistic latent semantic analysis
• 11.4.6 Recommender algorithms and evaluation metrics
• 11.4.6.1 User-based collaborative filtering
• 11.4.6.2 Item-based collaborative filtering
• 11.4.6.3 Enhanced collaborative filtering
• 11.4.7 Profile classification
• 11.5 Attack response and system robustness
• 11.5.1 Classification of attributes
• 11.5.1.1 Generic attributes
• 11.5.1.2 Model-derived attributes
• 11.5.2 Enhanced hybrid collaborative recommender systems
• 11.5.2.1 Hybrid recommendation algorithm
• 11.5.2.2 Push attacks against enhanced hybrid algorithm
• 11.5.3 Defense against profile injection attacks
• 11.5.3.1 Detection methods
• 11.5.3.2 Detection attributes for profile classification
• 11.6 Conclusion
• References

Inspec keywords: Big Data; parallel algorithms; security of data; recommender systems

Other keywords: user-based algorithms; item-based algorithms; profile injection attacks; Hadoop Distributed File System; attack models; big data recommender systems; security threat mitigation

Subjects: Information networks; Data security; Database management systems (DBMS); Parallel software; Search engines