Prophiler: a fast filter for the large-scale detection of malicious web pages

By Davide Canali, Marco Cova, Giovanni Vigna, Christopher Kruegel. 2011

430 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

Practical Evasion of a Learning-Based Classifier: A Case Study (2014, background): “Examples of such attacks have been previously studied under the assumption that an attacker has full knowledge about the deployed classifier.”
Graph based anomaly detection and description: a survey (2014, background): “…features are complementary to other techniques that use content-based features, such as the number of words, number of hyperlinks, text redundancy, etc. [Canali et al., 2011, Ntoulas et al., 2006], and content-free features, such as URLbased-only host and lexical features [Ma et al., 2009].”
Malicious URL Detection using Machine Learning: A Survey (2017, methodology): “[19] propose additional heuristic JavaScript features including: keywords-towords ratio, number of long strings, presence of decoding routines, shell code presence probability, number of direct string”
Detection of Malicious PDF Files Based on Hierarchical Document Structure (2013, methodology): “In contrast to prior work, the method we present in this article is intended for static detection of malicious PDF documents without a special consideration for JavaScript content.”
Cracking Classifiers for Evasion: A Case Study on the Google's Phishing Pages Filter (2016, background): “Various classifiers were trained for detecting malicious web pages [25], spam [54], phishing [58], malware [47], etc.”
Reviewer Integration and Performance Measurement for Malware Detection (2015, background): “which moderate access to expensive analysis in a virtual machine [5, 19].”
On the security relevance of weights in deep learning. (2020, background): “A simple drive-by download is enough to infect a machine with the malicious code [19], if no corresponding defense is in place [5, 16, 13].”
ZOZZLE: Fast and Precise In-Browser JavaScript Malware Detection (2011, methodology): “[4] present Prophiler, a lightweight static filter for malware.”
Comprehensive Analysis and Detection of Flash-Based Malware (2016, background): “Consequently, we do not discuss approaches for malicious JavaScript code in this paper and refer the reader to a wide range of research [7, 13, 26, 27, 35].”
URLNet: Learning a URL Representation with Deep Learning for Malicious URL Detection (2018, background): “Researchers have proposed several types of features for this task, including blacklist features [12, 26], lexical features [20, 26, 27, 41], host-based features [5, 26, 30], content features [3, 37, 40], and context and popularity based features [4, 7, 24].”