Zero-day malware detection using transferred generative adversarial networks based on deep autoencoders

JY Kim, SJ Bu, SB Cho - Information Sciences, 2018‏ - Elsevier
Detecting malicious software (malware) is important for computer security. Among the
different types of malware, zero-day malware is problematic because it cannot be removed …

A survey on zero-day polymorphic worm detection techniques

R Kaur, M Singh - IEEE Communications Surveys & Tutorials, 2014‏ - ieeexplore.ieee.org
Zero-day polymorphic worms pose a serious threat to the Internet security. With their ability
to rapidly propagate, these worms increasingly threaten the Internet hosts and services. Not …

Method and system for detecting malicious and/or botnet-related domain names

R Perdisci, W Lee - US Patent 10,027,688, 2018‏ - Google Patents
(57) ABSTRACT A method and system of detecting a malicious and/or botnet-related
domain name, comprising: reviewing a domain name used in Domain Name System (DNS) …

Obfuscated malware detection using deep generative model based on global/local features

JY Kim, SB Cho - Computers & Security, 2022‏ - Elsevier
As a large amount of malicious software (malware), including DDoS or Trojan horse pervade
in communication networks, several approaches based on global and local features have …

Method and system for detecting and responding to attacking networks

D Dagon, N Feamster, W Lee, R Edmonds… - US Patent …, 2013‏ - Google Patents
4,843,540 A 6, 1989 Stolfo 4,860,201 A 8, 1989 Stolfo et al. 5,363,473 A 11/1994 Stolfo et al.
5,497.486 A 3, 1996 Stolfo et al. 5,563,783 A 10, 1996 Stolfo et al. 5,668,897 A 9, 1997 …

Malware detection using deep transferred generative adversarial networks

JY Kim, SJ Bu, SB Cho - … , ICONIP 2017, Guangzhou, China, November 14 …, 2017‏ - Springer
Malicious software is generated with more and more modified features of which the methods
to detect malicious software use characteristics. Automatic classification of malicious …

Method and system for determining whether domain names are legitimate or malicious

M Antonakakis, R Perdisci, D Dagon, W Lee - US Patent 9,516,058, 2016‏ - Google Patents
4,843,540 A 6, 1989 Stolfo 4,860,201 A 8, 1989 Stolfo et al. 5,363,473 A 11/1994 Stolfo et al.
5,497.486 A 3, 1996 Stolfo et al. 5,563,783 A 10, 1996 Stolfo et al. 5,668,897 A 9, 1997 …

Method and system for detecting malicious domain names at an upper DNS hierarchy

M Antonakakis, R Perdisci, W Lee… - US Patent …, 2014‏ - Google Patents
7,277,961 7,331,060 7,372,809 7,383,577 7,424,619 7,426,576 7,448,084 7,483,947 7.487,
544 7,536,360 7,634,808 7,639,714 7,657,935 7,665,131 7,698.442 7,752,125 7,752,665 …

Method and system for detecting malware

E Antonakakis, R Perdisci, W Lee… - US Patent 8,578,497, 2013‏ - Google Patents
A system and method of analysis. NX domain names are collected from an asset in a real
network. The NX domain names are domain names that are not registered. The real network …

Method and system for network-based detecting of malware from behavioral clustering

R Perdisci, W Lee, G Ollmann - US Patent 8,826,438, 2014‏ - Google Patents
(57) ABSTRACT A computerized system and method for performing behav ioral clustering of
malware samples, comprising: executing malware samples in a controlled computer …