An Ontology-based Fuzzy Approach for Alert Verification and Correlation in RFID Systems

The proliferation of radio frequency identification (RFID) tags has implied that the pervasive RFID technology has become object of a broad range of malicious attacks, such as RFID malwares. This research is aimed at integrating the principles of both ontology and fuzzy logic modelling techniques in the intrusion detection paradigm to perform alert verification and correlation and determine this kind of attack. The proposed approach relies on three key points: (i) heterogeneous sensors diffused throughout the RFID infrastructure; (ii) fuzzy rules to handle imprecision and fuzziness in calculation of a confidence for each detected symptom in the verification procedure; (iii) a formal alert model, represented by means of an ontology and combined with fuzzy rules to represent knowledge for reasoning about complementary alert evidence and provide a comprehensive view of relevant symptoms indicating really potential attacks. Experimental tests are reported to give a proof of the feasibility of the methodology in the detection of malwares in RFID systems.