0.25
0.5
0.75
1.25
1.5
1.75
2
Knock It Off: Profiling the Online Storefronts of Counterfeit Merchandise
Published on Oct 07, 20141805 Views
We describe an automated system for the large-scale monitoring of Web sites that serve as online storefronts for spam-advertised goods. Our system is developed from an extensive crawl of black-market
Related categories
Chapter list
Knock It Off: Profiling the Online Storefronts of Counterfeit Merchandise 00:00
Problem in a nutshell 00:13
Counterfeit online storefronts 00:36
Counterfeit online storefronts 00:54
Counterfeit online storefronts 01:03
Who is running the store? 01:07
What is an affiliate program? 01:21
Key insight 01:50
Key insight 02:00
Our work 02:21
Challenges 03:02
Challenges 03:38
A role for machine learning 04:03
Feature extraction 05:16
Data set 06:11
Visualization of EvaPharmacy06:42
Proof-of-concept experiment 07:32
HTML distances are highly predictive 08:42
Mimicking an operational deployment 09:19
Mimicking an operational deployment 10:00
Mimicking an operational deployment 10:05
Classification in operational setting 10:07
One-shot learning 11:00
Conclusion 11:36
Thank you!12:40