Online examinations are an integral component of online learning environments and research studies have identified academic dishonesty as a critical threat to the credibility of such examinations. Academic dishonesty exists in many forms. Collusion is seen as a major security threat, wherein a student invites a third party for help or to impersonate him or her in an online examination. This work aims to investigate the authentication of students using text-based and image-based challenge questions. The study reported in this paper involved 70 online participants from nine countries completing a five week online course and simulating an abuse case scenario. The results of a usability analysis suggested that i) image-based questions are more usable than text-based questions (p < 0.01) and ii) using a more flexible data entry method increased the usability of text-based questions (p < 0.01). An impersonation abuse scenario was simulated to test the influence of sharing with different database sizes. The findings revealed that iii) an increase in the number of questions shared for impersonation increased the success of an impersonation attack and the results showed a significant linear trend (p < 0.01). However, the number of correct answers decreased when the attacker had to memorize and answer the questions in an invigilated online examination or their response to questions was timed. The study also revealed that iv) an increase in the size of challenge question database decreased the success of an impersonation attack (p < 0.01).