PhD Proposal: Understanding and Deterring Online Nigerian Scams

Talk
Young Sam Park
Time: 
11.24.2014 13:00 to 14:30
Location: 

AVW 3460

Nigerian scam, also known as advance fee fraud or 419 scam, is a prevalent form of online fraudulent activity that causes financial loss to individuals and businesses. Nigerian scam has evolved from simple untargeted email messages to more sophisticated scams targeted at users of classifieds, dating and other websites. Even though such scams are observed and reported by users frequently, the community's understanding of targeted Nigerian scams is limited since the scammers operate "underground".
To better understand the Nigerian scam eco-system and the different techniques the scammers use to deceive their victims, our preliminary works focused on two types of typical Nigerian scams: fake payment scams and rental scams targeted users on Craigslist. We built an automated scam data collection system and gathered large-scale fake payment scam emails. Using the system we posted honeypot ads on Craigslist and conversed automatically with the scammers. Through the email conversation, the system drew actual proofs of scam activities and collected additional information such as IP addresses and shipping addresses. Our analysis revealed that around 10 groups were responsible for nearly half of the over 13,000 total scam attempts we received. These groups used IP addresses and shipping addresses in both Nigeria and the U.S.
Using the extended automated scam data collection system, we crawled rental ads on Craigslist, identified rental scam ads amongst the large number of benign ads and conversed with the potential scammers. Through the analysis of the rental scams, we found several scam campaigns employing various operations and monetization methods. We also found that unlike fake payment scammers, most rental scammers were in the U.S.
The large-scale scam data and in-depth analysis provide useful insights on how to design effective detection and deterrence techniques. As the remaining work, we will propose a scam email and ad filtering system that leverages linguistic and various other features observed in our dataset. To evaluate the proposed filtering system, we will collaborate with a company that provides scam email filtering service to individual users. We will also study methods for deterring the scammers. To this end, we will perform large-scale experiment to assess the impact of various deterring cues, e.g., warning message in emails.
Examining Committee:
Committee Chair: - Dr. Elaine Shi
Dept's Representative - Dr. Hal Daume
Committee Members: - Dr. Jonathan Katz
- Dr. Damon McCoy
- Dr. Markus Jakobsson