Guilt by association: large scale malware detection by mining file-relation graphs

By Acar Tamersoy, Kevin A. Roundy, Duen Horng Chau. 2014

175 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, Signal Processing

How researchers see this paper

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

In Computer Networks and Communications

In Information Systems

In Signal Processing

Citations in the corpus

Attacking Graph-based Classification via Manipulating the Graph Structure (2019, methodology): “Roughly speaking, there are two categories of graph-based classiﬁcation methods, i.e., collective classiﬁcation [1,9,10, 14,22,23,29,34,39,45,57,62–65,69,71] and graph neural network [6,36,50,66].”
When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attacks (2018, background): “ML-based systems employed in the security industry [21, 10, 45, 39, 12] often combine undisclosed and known features to render attacks more difficult.”
Survey on the Usage of Machine Learning Techniques for Malware Analysis (2017, methodology): “properly tune belief propagation algorithm and improve it with respect to the approach used in [73] and other classication algorithms (e.”
Deep Learning for Anomaly Detection (2020, background): “These labeled data provide important knowledge of anomaly and can be a major driving force to lift detection recall rates [112, 114, 115, 145, 147].”
Deep Anomaly Detection with Deviation Networks (2019, background): “ble learning of the anomaly scores in an end-to-end fashion. 2.3 Anomaly Detection with Limited Data Only a few studies have been done on performing anomaly detection with a few labeled anomalies. In [16, 26], a small set of labeled anomalies is incorporated into a belief propagation process to achi”
A Survey on Malware Detection Using Data Mining Techniques (2017, methodology): “…intelligent malware detection systems [Schultz et al. 2001; Kolter and Maloof 2004; Karim et al. 2005; Lee and Mody 2006; Ye et al. 2007; Moskovitch et al. 2008a; Kolbitsch et al. 2009; Ye et al. 2010, 2011; Karampatziakis et al. 2013; Tamersoy et al. 2014; Saxe and Berlin 2015; Ni et al. 2016].”
Graph-based Security and Privacy Analytics via Collective Classification with Joint Weight Learning and Propagation (2018, methodology): “In Step III, these LBP-based methods [2], [5], [15], [23]– [25], [29] leverage either a standard LBP [46] or an optimized LBP [17], [18], [20], [47], [48] to propagate the reputation scores among the weighted graph.”