We introduce the concept of reliability in watermarking as the ability of assessing that a probability of false alarm is very low and below a given significance level. We propose an iterative and self-adapting algorithm which estimates very low probabilities of error. It performs much quicker and more accurately than a classical Monte Carlo estimator. The article finishes with applications to zero-bit watermarking (probability of false alarm, error exponent), and to probabilistic fingerprinting codes (probability of wrongly accusing a given user, code length estimation).