The Seeker's Dilemma: Realistic Formulation and Benchmarking for Hardware Trojan Detection

TL;DR

This paper reframes hardware Trojan detection as The Seeker’s Dilemma, a Hide&Seek game on graphs where the defender cannot know a priori if a circuit is HT-infected. It introduces Seeker1, a realistic benchmark with mixed HT-free and HT-infected nets produced via functional restructuring, allowing evaluation under unknown $k$ ($k\ge 0$) and various detection strategies. The authors evaluate three detectors (HW2VEC, RL_HT_DETECT, DETERRENT) and perform PCA analyses to show that HT-infected and HT-free variants can be entangled by restructuring, highlighting the need for diverse, robust datasets and evaluation pipelines. The work provides a formal problem statement, a benchmarking workflow, baseline results, and a community-accessible dataset to drive more realistic_HT-detection research and benchmarking improvements.

Abstract

This work focuses on advancing security research in the hardware design space by formally defining the realistic problem of Hardware Trojan (HT) detection. The goal is to model HT detection more closely to the real world, i.e., describing the problem as "The Seeker's Dilemma" (an extension of Hide&Seek on a graph), where a detecting agent is unaware of whether circuits are infected by HTs or not. Using this theoretical problem formulation, we create a benchmark that consists of a mixture of HT-free and HT-infected restructured circuits while preserving their original functionalities. The restructured circuits are randomly infected by HTs, causing a situation where the defender is uncertain if a circuit is infected or not. We believe that our innovative dataset will help the community better judge the detection quality of different methods by comparing their success rates in circuit classification. We use our developed benchmark to evaluate three state-of-the-art HT detection tools to show baseline results for this approach. We use Principal Component Analysis to assess the strength of our benchmark, where we observe that some restructured HT-infected circuits are mapped closely to HT-free circuits, leading to significant label misclassification by detectors.

Figures (11)

• Figure 1: Comparison of a) current HT detection approaches with static HT benchmarks vs. b) our proposed HT detection flow, including restructured benchmarks with and without HTs
• Figure 2: $G_{HT}$, shown in red, is embedded in $G_{T}$.
• Figure 3: Possible outcomes of an HT detection trial.
• Figure 4: Two representations of a circuit with the same truth table. Representation #1 is aimed at improving the area in terms of comparatively fewer nodes, while representation #2 enhances delay with fewer logic levels
• Figure 5: The distribution of clean ISCAS-85 circuits vs. RL HTs generated by sarihi2022hardwaresarihi2023trojanframework after applying PCA analysis