A survey of intrusion detection techniques
Computers and Security
An Evolutionary Immune Network for Data Clustering
SBRN '00 Proceedings of the VI Brazilian Symposium on Neural Networks (SBRN'00)
Self-Nonself Discrimination in a Computer
SP '94 Proceedings of the 1994 IEEE Symposium on Security and Privacy
An Immunological Approach to Change Detection: Algorithms, Analysis and Implications
SP '96 Proceedings of the 1996 IEEE Symposium on Security and Privacy
A Sense of Self for Unix Processes
SP '96 Proceedings of the 1996 IEEE Symposium on Security and Privacy
Architecture for an Artificial Immune System
Evolutionary Computation
A Framework for Assessing RFID System Security and Privacy Risks
IEEE Pervasive Computing
RFID security and privacy: a research survey
IEEE Journal on Selected Areas in Communications
| Hi-index | 0.00 |
The current RFID systems are fragile to external attacks, due to the limitations of encryption authentication and physical protection methods used in implementation of RFID security systems. In this paper, we propose a collaborative RFID intrusion detection method that is based on an artificial immune system (AIS). The new method can enhance the security of RFID systems without need to amend the existing technical standards of RFID. Mimicking the immune cell collaboration in biological immune systems, RFID operations are defined as self and nonself antigens, representing legal and illegal RFID operations, respectively. Data models are defined for antigens' epitopes. Known RFID attacks are defined as danger signals represented by nonself antigens. We propose a method to collect RFID data for antigens and danger signals. With the antigen and danger signal data available, we use a negative selection algorithm to generate adaptive detectors for self antigens as RFID legal operations. We use an immune based clustering algorithm aiNet to generate collaborative detectors for danger signals of RFID intrusions. Simulation results have shown that the new RFID intrusion detection method has effectively reduced the false detection rate. The detection rate on known types of attacks was 98% and the detection rate on unknown type of attacks was 93%.