Summary Background Psoriasis is an emerging paradoxical side effect in patients with inflammatory bowel disease (IBD) when treated with anti‐TNF alpha. Patients with severe skin lesions unresponsive to topical therapy need to withdraw from treatment. Aim To estimate the incidence of paradoxical psoriasis in a large cohort of IBD patients treated with anti‐TNF alpha and to analyse its clinical correlates. Methods A retrospective cohort study on all IBD patients who started anti‐TNF alpha at our IBD Centre from January 2008 to December 2013 was performed. Proportional hazards regression models were used to estimate the association between each predictor and time to the development of psoriasis. Time‐dependent predictors were updated at each available time point. Results Four hundred and two patients were included. Participants contributed a total of 839 person‐years of follow‐up, during which 42 incident cases of psoriasis were recorded, with an incidence rate of five per 100 person‐years. Cox‐regression survival analysis revealed smoking as independent predictor of psoriasis (HR: 2.37, 95% CI: 1.36–4.48; P = 0.008). Conversely, concomitant immunosuppressive therapy was inversely related to psoriasis (HR: 0.33, 95% CI: 0.12–0.92; P = 0.03). Conclusions Paradoxical psoriasis is a relevant side effect of anti‐TNF alpha therapy, with an incidence rate of five per 100 person‐years. Smoking is confirmed as the main risk factor for developing lesions. The combination therapy with anti‐TNF alpha plus immunosuppressants is associated with a reduced risk of paradoxical psoriasis.