A statistical pattern based feature extraction method on system call traces for anomaly detection

2020 ◽  
Vol 126 ◽  
pp. 106348 ◽  
Author(s):  
Zhen Liu ◽  
Nathalie Japkowicz ◽  
Ruoyu Wang ◽  
Yongming Cai ◽  
Deyu Tang ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Anomaly Detection ◽  
Extraction Method ◽  
System Call ◽  
Feature Extraction Method ◽  
Statistical Pattern

A Sum-of-Squares Polynomial Approach for Road Anomaly Detection Using Vehicle Sensor Measurements

2017 ◽  
Author(s):  
Dule Shu ◽  
Constantino Lagoa ◽  
Timothy Cleary
Keyword(s):  
Feature Extraction ◽  
Anomaly Detection ◽  
Extraction Method ◽  
Sum Of Squares ◽  
New Method ◽  
Feature Points ◽  
Feature Extraction Method ◽  
Different Types ◽  
Simulation Results ◽  
Vehicle Sensor

This paper presents a new method for road anomaly detection. The existence of road anomalies is determined by the behaviors of vehicles. A special polynomial named Sum-of-Squares (SOS) polynomial is used as a metric to evaluate the normality of vehicle behaviors. The method can process multiple types of sensor measurements. A feature extraction method is used to obtain concise representations of the sensor measurements. These representations, called feature points, are used to calculate the value of the SOS polynomial. Simulation results have been shown to demonstrate that the proposed method can effectively detect different types of road anomalies.

scholarly journals An Improved Feature Extraction Approach for Web Anomaly Detection Based on Semantic Structure

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Zishuai Cheng ◽  
Baojiang Cui ◽  
Tao Qi ◽  
Wenchuan Yang ◽  
Junsong Fu
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Anomaly Detection ◽  
Language Processing ◽  
Web Application ◽  
Extraction Method ◽  
Domain Knowledge ◽  
Semantic Structure ◽  
Feature Extraction Method ◽  
Web Attacks

Anomaly-based Web application firewalls (WAFs) are vital for providing early reactions to novel Web attacks. In recent years, various machine learning, deep learning, and transfer learning-based anomaly detection approaches have been developed to protect against Web attacks. Most of them directly treat the request URL as a general string that consists of letters and roughly use natural language processing (NLP) methods (i.e., Word2Vec and Doc2Vec) or domain knowledge to extract features. In this paper, we proposed an improved feature extraction approach which leveraged the advantage of the semantic structure of URLs. Semantic structure is an inherent interpretative property of the URL that identifies the function and vulnerability of each part in the URL. The evaluations on CSIC-2020 show that our feature extraction method has better performance than conventional feature extraction routine by more than average dramatic 5% improvement in accuracy, recall, and F1-score.

Sign in / Sign up

Export Citation Format

Share Document