As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
Detection of unknown attacks in network traffic is gaining increasing importance as modern attacks are characterized by high variabilities and mutation rates. Traditional signature-based intrusion detection systems (IDS) are not able to detect unknown attacks due to failing availability of appropriate signatures. We present an alternative approach based on machine learning techniques which enable automatic construction of profiles for normal packet payloads and detection of deviations thereof. Experimental evaluation of our approach showed a remarkable detection accuracy at low false positive rates and a major improvement in comparison to the widely used open-source IDS Snort.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.