Recent advances in hardware attacks, such as cross talk and covert channel based attacks, expose the structural and operational vulnerability of analog and mixed-signal circuit elements to the introduction of malicious and untrustworthy behaviour at run-time, potentially leading to adverse physical, personal, and environmental consequences.One untrustworthy behaviour of concern, is the introduction of abnormal/unexpected frequencies to the signals at the analog/ digital interface of a SoC, realised through intermittent bit-flipping or stuck-at-faults in the middle and lower bits of these signals.In this paper, we study the impact of these actions and propose integrity monitoring of signals of concern based on analysing the temporal and arithmetic relations between their samples. This paper presents a hybrid software/ hardware machine-learning based framework that consists of two phases; a run-time monitoring phase, and a trustworthiness assessment phase. The framework is evaluated with three different applications and its effectiveness in detecting the untrustworthy behaviour of concern is verified. This framework is device, application, and architecture agnostic, and relies only on analysing the output of the analog front-end, allowing its implementation in SoCs with on-chip and custom analog front-ends as well as those with outsourced and commercial off-the-shelf (COTS) analog front-ends.