|
|
 |
| |
|
|
|
Computer Malicious Executables Detection based on Real-Valued Negative Selection Algorithm |
|
|
|
PP: 1089-1094 |
|
|
|
Author(s) |
|
|
|
Jinquan Zeng,
|
|
|
|
Abstract |
|
|
| How to detect computer malicious executables is an important research direction of computer security, especially, unknown
malicious executables and new variants. Inspired by biological immune systems, a based on real-valued negative selection algorithm
approach to detect malicious executables is proposed in this paper, which is referred to MEDRNS. In order to avoid detectors covering
self space, some of benign executables are used to build the profile of the system, and then based on the built profile of the system,
the detectors are generated. At the same time, using the variable-sized self radius to represent the self space, detectors have the more
quality. The approach can increase true-positive rate and decrease false-positive rate, and experimental results show that MEDRNS has
better detecting ability than that of the previous techniques. |
|
|
|
|
|
|
|
