A Needle is an Outlier in a Haystack: Hunting Malicious PyPI Packages with Code Clustering.
Wentao LiangXiang LingJingzheng WuTianyue LuoYanjun WuPublished in: ASE (2023)
Keyphrases
- outlier detection
- malicious code
- clustering algorithm
- k means
- clustering method
- source code
- novelty detection
- cluster analysis
- document clustering
- data clustering
- malicious behavior
- detecting outliers
- static analysis
- information theoretic
- search engine
- hierarchical clustering
- fuzzy clustering
- categorical data
- software engineering
- social networks
- data sets