Ready for emerging threats to recommender systems? A graph convolution-based generative shilling attack.
Fan WuMin GaoJunliang YuZongwei WangKecheng LiuXu WangPublished in: Inf. Sci. (2021)
Keyphrases
- recommender systems
- injection attacks
- countermeasures
- product recommendation
- data sparsity
- attack detection
- collaborative filtering
- malicious attacks
- denial of service attacks
- attack graph
- insider attacks
- security measures
- collaborative filtering algorithms
- cyber attacks
- matrix factorization
- user profiles
- data corruption
- graph representation
- generative model
- random walk
- attack scenarios
- graph structure
- graph theory
- unsupervised learning
- image processing
- information overload
- structured data
- user preferences
- directed graph
- convolution kernel
- network configuration
- data mining
- weighted graph
- cold start
- directed acyclic graph
- personalized recommendation
- security issues