Social Robotics focuses on improving the ability of robots to interact with humans, including the capacity to understand their human interlocutors. When endowed with such capabilities, social robots can be useful to their users in a large variety of contexts: as guides, play partners, home assistants, or, most importantly, when being used for therapeutic purposes.Socially Assistive Robots (SAR) aim to improve the quality of life of their users by means of social interactions. Vulnerable populations of users, like people requiring rehabilitation, therapy or permanent assistance, benefit the most from the aid of SARs. One of the responsibilities of such robots is to make sure their users respect their therapeutic and medical recommendations, and human users are not always cooperative. As it has been observed in previous studies, humans sometimes deceive their robot caretakers in order to avoid following their recommendations. The former therefore end up deteriorating their medical condition and render the latter incapable of fulfilling theirs duties. Therefore, SARs and especially their users would benefit if robots were able to detect deception in Human-Robot Interactions (HRI).This thesis explores the physiological and behavioural manifestations and cues associated to deception in HRI, based on previous research done in inter-human interactions. As we consider that it is highly important to not impair the quality of the interaction in any way, our work focuses on the evaluation of these manifestations by means of noninvasive and minimally-invasive devices, such as RGB, RGB-D and thermal cameras as well as wearable sensors.To this end, we have designed a series of in-the-wild interaction scenarios during which participants are enticed to lie. During these experiments, we monitored the participants' heart rate, respiratory rate, skin temperature, skin conductance, eye openness, head position and orientation, and their response time to questions using noninvasive and minimally-invasive devices and sensors. We attempted to correlate the variations of the aforementioned parameters to the veracity of the participants' answers and statements. Moreover, we have studied the impact of the nature of the interlocutor (human or robot) on the participants' manifestations.We believe that this thesis and our results represent a major step forward towards the development of robots that are able to establish the honesty and trustworthiness of their interlocutors, thus improving the quality of HRI and the ability of SARs to perform their duties and to improve the quality of life of their users.