Security vulnerabilities and countermeasures for approximate circuits

Approximate computing is an advanced computational technique that trades the accuracy of computation results for better utilization of system resources. It provides significant benefits for energy-efficient systems and is being considered for high speed and low power nanoscale integrated circuit (IC) designs. It is crucial for ICs to achieve high speed and low power, where some intrinsic errors are acceptable, such as (deep-) machine learning, image processing, communication, and other error-tolerant and cognitive applications. However, approximate computing also introduces security vulnerabilities mainly due to the fact that the uncertain and unpredictable intrinsic errors during approximate execution may be indistinguishable from malicious modification of the input data, the execution process, and the results. In this book chapter, we present a comprehensive analysis of security vulnerabilities in approximate computing. Specifically, the security threats in approximate circuits and approximate testing techniques are deeply investigated and analyzed. A countermeasure, a self-detection technique, to tampering attack is also proposed and an experiment is carried out to evaluate the effectiveness of the proposed method. Experimental results show that the proposed method is effective to the tampering attack.