Remote Fingerprinting on Internet-Wide Printers Based on Neural Network

Zhaoteng Yan, Shichao Lv, Yueyang Zhang, Hongsong Zhu, Limin Sun

Abstract: Nowadays, a large number of printers are connecting to the Internet. It is undoubtedly true that these online printers are facing severe cyber threats. However, the research/researchers so far cannot answer the current security status of Internet-wide printers. The principal difficulty is to identify the exact brand and model of online printers with high coverage, which is the primary element in vulnerability description. In this work, we design and implement a system called PrinterRadar. Based on Neural Network, PrinterRadar can automatically generate fingerprints from the application layer protocol banners of online printers, and the precision and recall rate of fingerprints can achieve 98% and 97%. By fingerprint matching with the banners which were collected from Censys and Shodan, PrinterRadar found that 508,719 printers were connected to the Internet, covering 92 printer brands and 4,188 printer models. As to the discovered printers, it is about twice the number of those detected by Censys and Shodan.