scholarly journals CLort: High Throughput and Low Energy Network Intrusion Detection on IoT Devices with Embedded GPUs

Author(s):  
Charalampos Stylianopoulos ◽  
Linus Johansson ◽  
Oskar Olsson ◽  
Magnus Almgren
2009 ◽  
Vol 32 (3) ◽  
pp. 397-405 ◽  
Author(s):  
Wen‐Jyi Hwang ◽  
Chien‐Min Ou ◽  
Ying‐Nan Shih ◽  
Chia‐Tien Dan Lo

Author(s):  
Venkatraman Subbarayalu ◽  
B Surendiran ◽  
P Arun Raj Kumar

Abstract The proliferation of Internet of Things (IoT) devices has led to many applications, including smart homes, smart cities and smart industrial control systems. Attacks like Distributed Denial of Service, event control hijacking, spoofing, event replay and zero day attacks are prevalent in smart environments. Conventional Network Intrusion Detection Systems (NIDSs) are tedious to deploy in the smart environment because of numerous communication architectures, manufacturer policies, technologies, standards and application-specific services. To overcome these challenges, we modeled the operational behavior of IoT network events using timed ACs and proposed a novel hybrid NIDS in this paper. A web server is integrated with IoT devices for remote access, and Constrained Application Protocol is employed in inter- and intra-smart device communication. Experiments are conducted in real time to validate our proposal and achieve 99.17% detection accuracy and 0.01% false positives.


2011 ◽  
Vol 403-408 ◽  
pp. 1985-1988
Author(s):  
Jing Jiao Li ◽  
Ho Cholman ◽  
Yong Chen ◽  
Song Ho Pak

Intrusion detection for network security is an application area demanding high throughput. The pattern matching in intrusion detection requires extremely high performance to process string matching. Most of pattern matching using software has many time complexities and cannot reach the requirements of high throughput. The pattern matching using hardware considerably improves the speed of matching and has several other advantages. This paper describes a FPGA-based pattern matching architecture, using hashing method called XOR Hashing. The proposed method updates new patterns without reconfiguration and processes the collision and has high matching performance. The proposed system implements the pattern matching by using Snort rule-set, an open source Network Intrusion Detection and has simulation processing on PC. Compared with existing hardware method, the results explained that our method has relatively high performance for the pattern matching and can else process the pattern matching with high performance on low–cost FPGA device.


Sign in / Sign up

Export Citation Format

Share Document