Tehničko veleučilište u Zagrebu · Zagreb

Reducing false rate packet recognition using Dual Counting Bloom Filter

izvorni znanstveni rad

izvorni znanstveni rad

Reducing false rate packet recognition using Dual Counting Bloom Filter

Vrsta prilog u časopisu
Tip izvorni znanstveni rad
Godina 2018
Časopis Telecommunications systems
Nadređena publikacija Telecommunication Systems
Volumen 68
Svesčić 1
Stranice str. 67-78
DOI 10.1007/s11235-017-0375-3
ISSN 1018-4864
EISSN 1572-9451
Status objavljeno

Sažetak

Distributed Denial of Service (DDoS) attacks are a serious threat to Internet security. A lot of research effort focuses on having detection and prevention methods on the victim server side or source side. The Bloom filter is a space-efficient data structure used to support pattern matching problems. The filter is utilised in network applications for deep packet inspection of headers and contents and also looks for predefined strings to detect irregularities. In intrusion detection systems, the accuracy of pattern matching algorithms is crucial for dependable detection of matching pairs, and its complexity usually poses a critical performance bottleneck. In this paper, we will propose a novel Dual Counting Bloom Filter (DCBF) data structure to decrease false detection of matching packets applicable for the SACK2 algorithm. A theoretical evaluation will determine the false rate probability of detection and requirements for increased memory. The proposed approach significantly reduces the false rate compared to previously published results. The results indicate that the increased complexity of the DCBF does not affect efficient implementation of hardware for embedded systems that are resource constrained. The experimental evaluation was performed using extensive simulations based on real Internet traces of a wide area network link, and it was subsequently proved that DCBF significantly reduces the false rate.

Ključne riječi

DDoS ; SYN flooding ; Hash-based detection ; Bloom filter