Learning a Neural-network-based Representation for Open Set Recognition
Preprint
Abstract
Open set recognition problems exist in many domains. For example in security, new malware classes emerge regularly; therefore malware classification systems need to identify instances from unknown classes in addition to discriminating between known classes. In this paper we present a neural network based representation for addressing the open set recognition problem. In this representation instances from the same class are close to each other while instances from different classes are further apart, resulting in statistically significant improvement when compared to other approaches on three datasets from two different domains.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Generative OpenMax for Multi-Class Open Set Classification2017
- A Survey of Stealth Malware Attacks, Mitigation Measures, and Steps Toward Autonomous Open World SolutionsIEEE Communications Surveys & Tutorials, 2016
- Multi-class Open Set Recognition Using Probability of Inclusion2014
- Face recognition for web-scale datasetsComputer Vision and Image Understanding, 2014
- Toward Open Set RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Automatic analysis of malware behavior using machine learningJournal of Computer Security, 2011