While online approaches to data collection provide benefits over paper-based surveys in terms of subject anonymity, the sample that is obtained using Internet-based methods should be examined for eligibility even if participants complete a verification questionnaire before entering the study.  In this presentation, the process of identifying potentially fraudulent entries will be applied to data from a recent survey of men who have sex with men (MSM) and their sexual behavior.  The effects of these possibly ineligible entries on estimates of sexual behavior will also be examined.  Considerations for improving fraud detection during survey development, implementation, and analysis will be summarized.