DBF: A general framework for anomaly detection in RFID systems

Min Chen, Jia Liu, Shigang Chen, Yan Qiao, Yuanqing Zheng

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

11 Citations (Scopus)


RFID technologies are making their way into numerous applications, including inventory management, supply chain, product tracking, transportation, logistics, etc. One important application is to automatically detect anomalies in RFID systems, such as missing tags, unknown tags, or cloned tags due to theft, management error, or targeted attacks. Existing solutions are all designed to detect a certain type of RFID anomalies, but lack a general functionality for detecting different types of anomalies. This paper attempts to propose a general framework for anomaly detection in RFID systems, thereby reducing the complexity for readers and tags to implement different anomaly-detection protocols. We introduce a new concept of differential Bloom filter (DBF), which turns physical-layer signal data into a segmented Bloom filter that encodes the IDs of abnormal tags. As a case study, we propose a protocol that builds DBF for identifying all missing tags in an efficient way. We implement a prototype for missing-tag identification using USRP and WISP tags to verify the effectiveness our protocol, and use large-scale simulations for performance evaluation. The results show that our solution can significantly improve time efficiency, when comparing with the best existing work.
Original languageEnglish
Title of host publicationINFOCOM 2017 - IEEE Conference on Computer Communications
ISBN (Electronic)9781509053360
Publication statusPublished - 2 Oct 2017
Event2017 IEEE Conference on Computer Communications, INFOCOM 2017 - Atlanta, United States
Duration: 1 May 20174 May 2017


Conference2017 IEEE Conference on Computer Communications, INFOCOM 2017
Country/TerritoryUnited States

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering


Dive into the research topics of 'DBF: A general framework for anomaly detection in RFID systems'. Together they form a unique fingerprint.

Cite this