Polonium: Tera-Scale Graph Mining for Malware Detection

By Duen Horng Chau, Carey Nachenberg, Jeffrey Wilhelm, Adam Wright, Christos Faloutsos. 2013

55 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attacks (2018, background): “by incorporating undisclosed features for malware detection [10].”
Graph Classification using Structural Attention (2018, background): “chemoinformatics [11], social network analysis [2], urban computing [3], and cyber-security [6] can all be naturally represented as labeled graphs.”
A Survey on Malware Detection Using Data Mining Techniques (2017, methodology): “Besides file contents, file-to-machine relation graphs [Chau et al. 2011] and file-to-file relation graphs [Ye et al.”
Survey on the Usage of Machine Learning Techniques for Malware Analysis (2017, methodology): “[11] apply it for detecting malware on terabytes of data, while both [22] and [24] adapt belief propagation to malware analysis by proposing new mathematical representations.”
Before we knew it: an empirical study of zero-day attacks in the real world (2012, background): “For example, the fact that zero-day attacks are rare events, but that the new exploits are re-used for multiple targeted attacks, suggests that techniques for assigning reputation based on the prevalence of files [9] can reduce the effectiveness of the exploit.”
Digital technologies and artificial intelligence’s present and foreseeable impact on lawyering, judging, policing and law enforcement (2015, unknown): “Polonium (Chau et al. 2010; Nissan 2012: Sec.”