An Integrated Approach of Threat Analysis for Autonomous Vehicles Perception System

Abstract

Automated vehicles are a revolutionary step in mobility, providing a safe and convenient riding experience while keeping the human-driving task minimal to none. Therefore, these intelligent vehicles are equipped with sophisticated perception sensors (e.g., cameras and radars), high-performance computers, artificial intelligence (AI)-driven algorithms, and connectivity with other internet-of-things (IoT) devices. This makes autonomous vehicles (AVs) a special kind of cyber-physical system (CPS) that is moving at speed in highly interactive and dynamic environments (e.g., public roads). Thus, AV is a potential target for cyber attackers to weaponize, compromising safety and mobility on the road. The first step in addressing this problem is to have a robust threat modeling framework that can address the evolving cyber-physical threats, especially to AV applications. In this regard, two areas are studied in this paper: the common practice of threat modeling in automotive and the ISO/SAE 21434 standard, and sensors and machine learning (ML) algorithms for AV perception systems and potential cyber-physical attacks. A comparative threat analysis for an AV perception system with the ISO/SAE 21434 standard and a system-theoretic process analysis for security (STPA-Sec) approach is also demonstrated in this paper. Based on the analysis, this paper proposes a robust threat analysis and risk assessment framework with mathematical modeling to identify cyber-physical threats to AV perception systems that are critical for the driving behaviors and complex interactions of AVs in their operational design domain.

STPA for Learning-Enabled Systems: A Survey and A New Practice

“…With the advancement of ML, in addition to safety, security and privacy have emerged as the two attributes of growing interest, which encompass guarding against external system breaches and noticing the privacy implications of system usage. This is exemplified by the development of STPA-sec [44], [31], [50], [54], [26] and STPA-priv [39], [53], indicating the flexibility of STPA in terms of accommodating attributes beyond safety. STPA-sec focuses on analysing the vulnerability of the system to external attacks, while STPA-priv highlights the data privacy issues in the system.…”

“…b) Object Under Study: Autonomous (ground) vehicles are the most commonly studied object by STPA due to their popularity, complexity and pressing need for safety [31], [59], [1], [54], [50], [38], [32], [4], [56], [19], [25], [26], [46]. Autonomous ships and drones are also studied in [58], [49], [27], [61], [5] and [16], respectively.…”

Anomaly Detection in Connected and Autonomous Vehicles: A Survey, Analysis, and Research Challenges

“…This framework excels in identifying risks such as cyberattacks against AI algorithms, unauthorized access to vehicle control commands and its sensors. STPA-Sec provides a comprehensive hazard assessment, addressing concerns related to incorrect decisions, system failures and malicious interventions [139]. Additionally, their focus on developing and implementing security controls ensures a strong defense against identified risks.…”

Complying with ISO 26262 and ISO/SAE 21434: A Safety and Security Co-Analysis Method for Intelligent Connected Vehicle

“…It is an extension of STPA, customized to include security analysis. STPA-Sec maintains the same four basic steps as STPA, but essentially introduces threat/vulnerability identification in the last step [ 44 ]. Sahay et al [ 45 ] evaluated and compared the application of STPA-Sec, STRIDE, and CORAS in identifying threats and vulnerabilities to the cybership system.…”