Adversarial Hardware With Functional and Topological Camouflage

Abstract

The lately attack on the Qualcomm’s Snapdragon chip reminds us security risks related to digital arithmetic circuits. Most system designers neglect the employed computer arithmetic algorithms or their implementation details. Arithmetic circuits are therefore usually used as “black box” units that are instantiated by third-party intellectual-property core or electronic design-automation tool vendors. In this brief, we propose the first most-significant digit-first arithmetic-based hardware Trojan attack by addressing the questions of where to insert and with what . First, we demonstrate how functional camouflage is achieved. Certain arithmetic modules can be quietly replaced with functionally equivalent ones, which we term functionally camouflaged Trojans. Next, we introduce a topologically camouflaged Trojan by employing graph-centrality analysis on rare behaviours in the circuit. The proposed approach is applicable to any digital computing scenarios. Experimental results on a financial computing system demonstrate that completely inaccurate numeric results are yielded, along with an up-to 91.6% numerical error tested.