Detection of Malicious PDF Files Based on Hierarchical Document Structure

By Nedim Srndic, Pavel Laskov. 2013

213 citations recorded by the source corpus.

Subfields: Privacy & Security

How researchers see this paper

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

In Privacy & Security

1. Battista Biggio
2. Fabio Roli
3. Davide Maiorca
4. Giorgio Giacinto
5. Giorgio Fumera
6. Taesoo Kim
7. Meng Xu
8. Bo Li

Citations in the corpus

• Stealing Hyperparameters in Machine Learning (2018, neutral): “, PDFrate [47] or Hidost [50]).”
• Is Feature Selection Secure against Training Data Poisoning? (2015, methodology): “For instance, detection of malware in PDF files relies on the analysis of the PDF logical structure, which consists of a large set of different kinds of objects and metadata, yielding a high-dimensional data representation (Smutz & Stavrou, 2012; Maiorca et al., 2012; 2013; Šrndić & Laskov, 2013).”
• Automatically Evading Classifiers: A Case Study on PDF Malware Classifiers (2016, methodology): “9% accuracy in a PDF malware classification task using an SVM-RBF model with structural path features [28].”
• Adversarial Detection of Flash Malware: Limitations and Open Issues (2017, methodology): “With respect to SWF malware, static analysis showed promising results at detecting malicious samples in the wild by extracting information either from the structure of the file [27] or from the ActionScript bytecode [34].”
• Evading Classifiers by Morphing in the Dark (2017, methodology): “To study the feasibility and effectiveness of our proposed approaches, we conduct experimental evaluation on two well-known PDF malware classifier, namely PDFrate [27] and Hidost [29].”
• Adversarial Feature Selection Against Evasion Attacks (2016, background): “ticular, on the set of embedded keywords [17], [18].”
• On Evaluating Adversarial Robustness (2019, background): “This long line of research (Dalvi et al., 2004; Lowd & Meek, 2005; Barreno et al., 2006; 2010; Globerson & Roweis, 2006; Kołcz & Teo, 2009; Barreno et al., 2010; Biggio et al., 2010; Šrndic & Laskov, 2013) has recently begun seeing significant study as machine learning becomes more widely used.”
• Towards Making Systems Forget with Machine Unlearning (2015, neutral): “We are aware of other machine learningbased PDF detection engines [66, 68] after PJScan, however we choose PJScan because it is open-source and unique in adopting one-class machine learning.”
• Feature Conservation in Adversarial Classifier Evasion: A Case Study (2017, methodology): “Several PDF malware classifiers have been proposed [6], [31].”
• A Survey on Security Threats and Defensive Techniques of Machine Learning: A Data Driven View (2018, methodology): “, spam detection [6], PDF malware detection [24], etc.”
• Intriguing Properties of Adversarial ML Attacks in the Problem Space (2019, unknown): “Classifier g SVM-RBF (Hidost [57]), RF (PDFRate [56]).”
• Towards Adversarial Malware Detection (2018, methodology): “Scan 2011 Static Poppler JS-based SVM Maiorcaet al.[64] Slayer 2012 Static PDFID Structural Random Forest Smutz and Stavrou[82] PDFRate-v1 2012 Static Custom Structural Random Forest Šrndić and Laskov[85,95] Hidost 2013 Static Poppler Structural Random Forest Coronaet al.[22] Lux0R 2014 Dynamic Phon”