Using Diverse Detectors for Detecting Malicious Web Scraping Activity
Pedro Marques, Zayani Dabbabi, Miruna-Mihaela Mironescu, Olivier Thonnard, Frances Buontempo, Ilir Gashi, Alysson Bessani · 2018
We present ongoing work about how the use of diverse tools may help with detecting malicious web scraping behavior. We use a real dataset of Apache HTTP Access logs for an e-commerce application provided by Amadeus, a large multinational IT provider for the global travel and tourism industry. Two tools have been used to detect scraping activities based on the HTTP requests: a commercial tool from Distil Networks, and an in-house tool called Arcane. Preliminary results suggest there is considerable diversity in alerting behavior of these tools.