Assessing the effect of cybersecurity training on End-users: A Meta-analysis

Cybersecurity behaviour of end-users continues to be a growing topic of conversation, both in organisations and in academia, as end-users are often said to be the last line of defence against cyberattacks. Unfortunately, endusers are often not aware that they engage in risky cyber behaviours and can, in turn, make themselves and the organisations that they work for vulnerable. Attempting to change end-user behaviour through training programs has become common practice in many organisations, a trend that is reflected in the academic literature as well. While a variety of literature reviews on the topic are available, an assessment of the effectiveness of these training programs through a meta-analysis has so far not been conducted. We carried out a meta-analysis based on a systematic literature review on the topic and an updated literature search in order to assess the overall effectiveness of cybersecurity training programs. We identified 69 studies that were eligible for inclusion. Our analysis shows that training overall has a positive effect on end-users (d = 0.75, 95%CI [0.58, 0.92]), particularly when assessing predictors of behaviour such as attitudes or knowledge (d = 1.02, 95%CI [0.58, 1.46]). Interestingly, studies assessing changes in behaviour are not able to match these results (d = 0.36, 95%CI [-0.09, 0.80]), showcasing a clear inability of current training approaches to change behaviour. The effect sizes obtained in this meta-analysis can act as smallest effect sizes of interest (SESOIs) for future research on end-user cybersecurity training. Further findings with regards to the effectiveness of individual training methods and other moderators are discussed.