Abstract
This paper presents AVATAR, a learning-assisted Trojan testing flow to detect hardware Trojans placed into fabricated ICs at an untrusted foundry, without needing a Golden IC. AVATAR is a side-channel delay-based testing solution that is assisted by a learning model (process watchdog) for tracking the process drift and systematic process variation. AVATAR’s process watchdog model is trained using a limited number of test samples, collected at test time, to tightly correlate the Static Timing Analysis results (generated at design time) to the test results (generated from clock frequency sweeping test). The experimental results confirm that AVATAR detects over 98% of (small) Trojans inserted in the selected benchmarks. We have complemented our proposed solution with a diagnostic test that 1) further reduces the false-positive rate of AVATAR Trojan detection to zero or near zero, and 2) pinpoints the net-location of the Trojan Trigger or Payload.
Highlights
To reduce the fabrication cost, scale with market demand, and access to the state-of-the-art technology, the manufacturing supply chain of Integrated Circuits (IC) is widely and globally distributed [1]
This section depicts the accuracy of the Neural Network (NN)-Watchdog in tracking the process drift, and presents the results of applying our proposed test flow, AVATAR, for Trojan detection
In this paper, we presented a promising learning-assisted methodology for Trojan detection based on side-channel delay analysis that does not require the availability and usage of a Golden IC
Summary
To reduce the fabrication cost, scale with market demand, and access to the state-of-the-art technology, the manufacturing supply chain of Integrated Circuits (IC) is widely and globally distributed [1]. Such broad globalization has raised many concerns over the security and trustworthiness of ICs when untrusted providers and facilities are included in the supply chain [2]. The concerns over Hardware Trojan was raised by US DoD in 2005 [3] The spectrum of harm caused by HT is broad It can range from passive HT for activity monitoring or stealing information to weaponized HT that could cause catastrophic consequences in the critical military, space, or medical applications [4]. Thereby, detecting HT is highly crucial, and it has become a significant concern for governments and industries
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
