SIGL: Securing Software Installations Through Deep Graph Learning
arXiv:2008.11533
Abstract
Many users implicitly assume that software can only be exploited after it is installed. However, recent supply-chain attacks demonstrate that application integrity must be ensured during installation itself. We introduce SIGL, a new tool for detecting malicious behavior during software installation. SIGL collects traces of system call activity, building a data provenance graph that it analyzes using a novel autoencoder architecture with a graph long short-term memory network (graph LSTM) for the encoder and a standard multilayer perceptron for the decoder. SIGL flags suspicious installations as well as the specific installation-time processes that are likely to be malicious. Using a test corpus of 625 malicious installers containing real-world malware, we demonstrate that SIGL has a detection accuracy of 96%, outperforming similar systems from industry and academia by up to 87% in precision and recall and 45% in accuracy. We also demonstrate that SIGL can pinpoint the processes most likely to have triggered malicious behavior, works on different audit platforms and operating systems, and is robust to training data contamination and adversarial attack. It can be used with application-specific models, even in the presence of new software versions, as well as application-agnostic meta-models that encompass a wide range of applications and installers.
arXiv comment18 pages, to appear in the 30th USENIX Security Symposium (USENIX Security '21)
References in corpus (8)
- Distributed Representations of Words and Phrases and their Compositionality
- Adversarial Attacks on Neural Networks for Graph Data
- Head/tail Breaks: A New Classification Scheme for Data with a Heavy-tailed Distribution
- Learning to Execute
- SAQL: A Stream-based Query System for Real-Time Abnormal System Behavior Detection
- Unsupervised Learning of Anomaly Detection from Contaminated Image Data using Simultaneous Encoder Training
- RSM-GAN: A Convolutional Recurrent GAN for Anomaly Detection in Contaminated Seasonal Multivariate Time Series
- Few-Shot Representation Learning for Out-Of-Vocabulary Words