High cost differentials are causing many steps of IC manufacturing to increasingly move overseas. This project considers the problem of evaluating trustworthiness of digital ICs fabricated by untrusted vendors who may insert hardware Trojans. The proposed EDICT framework (Evaluation and Design of IC's for Trustworthiness) tackles two main challenges, namely the unavailability of a gold-standard chip combined with high process variations, and the fact that Trojans are introduced by intelligent adversaries. EDICT exploits the key difference between the impact on circuit parameters of Trojans and process variations - universal shift vs. random - to detect Trojans, including those causing deviations smaller than process variations. In particular, this project is developing new techniques to identify effective measurements - sequences of values applied at IC inputs and parameters measured - for evaluation of chip's trustworthiness. This project represents a radical extension of techniques for generating vectors for high-volume-manufacturing testing by focusing on new targets that capture all possible Trojans, developing the first suite of techniques to characterize and identify Trojans in a non-destructive manner, and developing the first methods to identify additional unauthorized functionality. By providing the technical infrastructure to evaluate trustworthiness of ICs, this project enables defense and civilian sectors to exploit global semiconductor industry at reduced risk. Trustworthy digital systems bring many benefits to society. They improve many essential services - health, security, education, etc. - and bring lower costs. Finally, this project trains graduate students in developing, and defense and industry experts in using, new approaches and tools for evaluating IC trustworthiness.
Our research considered the problem of evaluating trustworthiness of digital ICs fabricated by untrusted vendors. In particular, we developed a theory and conceptual framework that will form the foundation of an extensive, effective, and extendible toolkit for trustworthy design and trustworthiness evaluation of chips fabricated for designs that might have been tampered by resourceful and intelligent adversaries. More precisely, we developed new principles for characterization of Trojans inserted by intelligent adversaries using our new notion of surrogates. We also identified several principles for selection of target surrogates and generation of vectors to enable identification of Trojans in presence of increasing levels of process variations, which cannot be detected by classical testing and validation approaches. We incorporated our early results in a prototype tool and demonstrated the benefits of our approach. Broader impacts of this research included: (1) Development of a technical infrastructure to establish trustworthiness of integrated circuits, making it possible for defense and civilian sectors to exploit the global semiconductor industry, (2) Training students and giving tutorials for defense and industry experts and academic researchers, to train them in our new approach and tools for ensuring trustworthiness of ICs, and (3) Publishing our findings and results in various archival journals and conference proceedings.
