Generating A New Shilling Attack for Recommendation Systems
Source abstract
Abstract
A collaborative filtering-based recommendation system has been an integral part of e-commerce and e-servicing. To keep the recommendation systems reliable, authentic, and superior, the security of these systems is very crucial. Though the existing shilling attack detection methods in collaborative filtering are able to detect the standard attacks, in this paper, we prove that they fail to detect a new or unknown attack. We develop a new attack model, named Obscure attack, with unknown features and observed that it has been successful in biasing the overall top-N list of the target users as intended. The Obscure attack is able to push target items to the top-N list as well as remove the actual rated items from the list. Our proposed attack is more effective at a smaller number of k in top-k similar user as compared to other existing attacks. The effectivity of the proposed attack model is tested on the MovieLens dataset, where various classifiers like SVM, J48, random forest, and naïve Bayes are utilized.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Recommender Systems and Techniques · Caching and Content Delivery · Image Retrieval and Classification Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (27)
Show source-provided references
1. Shilling attack based on item popularity and rated item correlation against collaborative filtering10.1007/s13042-018-0861-2 ↗
2. Performance of recommender algorithms on top-n recommendation tasks
3. Evaluation of item-based top-n recommendation algorithms
4. Local item-item models for top-n recommendation
5. A comparative study of different similarity metrics in highly sparse rating dataset
6. Item-based top-n recommendation algorithms10.1145/963770.963776 ↗
7. Zayed · Web, Artificial Intelligence and Network Applications (WAINA 2020). Advances in Intelligent Systems and Computing · 2020 · 1150 · 429
8. Detection of obfuscated attacks in collaborative recommender systems
9. Singh · New Age Analytics: Transforming the Internet Through Machine Learning, IoT, and Trust Modeling · 2020 · 18310.1201/9781003007210-8 ↗
10. Recommender systems: Attack types and strategies
11. Graph-based detection of shilling attacks in recommender systems
12. Attacks and remedies in collaborative recommendation10.1109/MIS.2007.45 ↗
13. Effective attack models for shilling item-based collaborative filtering systems
14. Toward trustworthy recommender systems: An analysis of attack models and algorithm robustness10.1145/1278366.1278372 ↗
15. Shilling attack models in recommender system
16. Shilling recommender systems for fun and profit
17. Segment-based injection attacks against collaborative filtering recommender systems
18. Classification features for attack detection in collaborative recommender systems
19. Shilling attack detection in collaborative recommender systems using a meta learning strategy
20. Detection of shilling attacks in recommender systems via spectral clustering
21. Preventing shilling attacks in online recommender systems
22. Shilling attack detection for recommender systems based on credibility of group users and rating time series10.1371/journal.pone.0196533 ↗
23. Evaluating recommender system stability with influence-guided fuzzing10.1609/aaai.v33i01.33014934 ↗
24. Evaluation of collaborative filtering based recommender systems against segment-based shilling attacks
25. Improving the accuracy of collaborative filtering-based recommendations by considering the temporal variance of top-n neighbors
26. A novel neighborhood calculation method by assessing users’ varying preferences in collaborative filtering
27. Enhancing recommendation accuracy of item-based collaborative filtering using bhattacharyya coefficient and most similar item10.1007/s10489-020-01775-4 ↗