alhussain-shaikh / HardwareTrojanDetection-

This repository contains code and resources related to the detection of embedded Malware/Trojan in hardware devices used in the Power Sector. The project focuses on identifying and mitigating cybersecurity threats in the semiconductor industry.

Silicon Decrypters - Detection of Embedded Malware/Trojan in Hardware Devices

Description

This repository contains code and resources related to the detection of embedded Malware/Trojan in hardware devices used in the Power Sector. The project focuses on identifying and mitigating cybersecurity threats in the semiconductor industry.

Hardware Trojan Detection Techniques:

1. The Project describes the use of power and side channel analysis for detecting hardware Trojans by monitoring power usage and path delays.
2. Automatic Test Pattern Generation (ATPG) is utilized to reveal potential malicious circuitry and avoid exhaustive test cases.
3. The D Algorithm is mentioned for obtaining actual test cases to deal with faults like Stuck at 0 & Stuck at 1.
4. A feature is highlighted to represent the circuit into a graph for simulation and storing information about neighboring elements.

Embedded Malware Detection:

1. We introduces the Embedded C Flaw Finder and Python code analysis for identifying security flaws in C/C++ code.
2. FlawFinder is used to detect potential vulnerabilities in the source code and generate a summary report for developers to secure their software.
3. The Raspberry Pi Foundation's preference for Python is mentioned due to its power, versatility, and ease of use.
4. Tools like CProfile, Memory Profiler, and Line Profiler are listed for code analysis and optimization.

Innovative Trojan Detection Method:

An innovative Graph Neural Network (GNN)-based method is introduced for Trojan detection in RTL and gate-level netlists using Data Flow Graph (DFG) representations. The method eliminates the need for a golden reference in Trojan detection. Steps include DFG extraction from hardware design, feature extraction, and classification using a GNN framework with graph convolution layers and attention-based graph pooling.

Project Details:

1. The project theme is focused on Blockchain & Cybersecurity, addressing the problem statement of detecting embedded Malware/Trojan in hardware devices used in the Power Sector. Decentralized Security and Data Storage:

2. We have used the Inter Planetary File System (IPFS) as a decentralized database storage mechanism similar to blockchain networks but more cost-effective and secure.