Hardware Trojan horse detection method based on lifting algorithm

Abstract

The invention discloses a hardware Trojan horse detection method based on a lifting algorithm. Processing according to the topological structure of the integrated circuit to obtain a first controllability value, a second controllability value and an observability value of each node of the integrated circuit; performing density-based clustering according to the first controllability value, the second controllability value and the observability value of each node of the integrated circuit to obtain a matrix of band class distances; and training classification is performed by adopting a weak classifier, the weak classifier is combined to obtain a final classifier, and then the final classifier is adopted to process the matrix X'with the class distance obtained by processing the to-be-detectedintegrated circuit so as to obtain the hardware Trojan horse detection result of the to-be-detected integrated circuit. The method provided by the invention has higher accuracy than a bypass analysismeans under a large sample condition.

Description

technical field [0001] The invention belongs to the technical field of integrated circuit detection, and in particular relates to a hardware Trojan horse detection method based on a lifting algorithm. Background technique [0002] With the continuous development of the information society, the scale of integrated circuits is showing an explosive increase trend, and its security is constantly being challenged. A hardware Trojan horse refers to a circuit component that is deliberately added to a hardware circuit, or a defect or hidden danger left unintentionally during the development of an integrated circuit. Compared with traditional software Trojan horses, hardware Trojan horses have the characteristics of concealment, low trigger rate, complicated mechanism of action, and great harm once triggered. [0003] Existing hardware Trojan detection technologies are mainly divided into four categories, namely, physical detection and bypass analysis that require tools, and test-ba...

AI Technical Summary

Problems solved by technology

The functional test method requires an automatic test platform, which is tested by an exhaustive method of input test vectors, but due to the relatively large test time and test quantity, the application range is limited

Built-in self-test technology does not require external tools, but modules for testing must be added in the production process of the chip, and the detection of the overall circuit cannot be realized

Physical testing and bypass analysis require the use of high-precision testing instruments. The main feature of physical testing is reverse engineering analysis, but it is only suitable for chips with relatively simple structures, but because it requires more investment and testing time-consuming, and uncommonly used

The detection accuracy of bypass analysis is high, and at the same time, there are relatively few conditional restrictions, and the detection can be realized without triggering the Trojan horse. However, the physical quantities required by bypass analysis are difficult to observe accurately and are easily affected by noise, so its practical application is also difficult. subject to limitations

Images