Showcasing standards and approaches for cybersecurity, safety, and privacy issues in connected and autonomous vehicles

• URL: http://arxiv.org/abs/2508.01207v1
• Date: Sat, 02 Aug 2025 05:45:50 GMT
• Title: Showcasing standards and approaches for cybersecurity, safety, and privacy issues in connected and autonomous vehicles
• Authors: Ricardo M. Czekster,
• Abstract summary: This paper aims to bridge cybersecurity, safety, and privacy concerns in Connected and Autonomous Vehicles (CAV) with respect to Risk Assessment (RA) and Threat Modelling (TM)<n>We highlight latest standards and approaches in RA and TM research to tackle complex attack surfaces as the ones posed by automotive settings.
• Score: 0.24475591916185502
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In the automotive industry there is a need to handle broad quality deficiencies, eg, performance, maintainability, cybersecurity, safety, and privacy, to mention a few. The idea is to prevent these issues from reaching end-users, ie, road users and inadvertently, pedestrians, aiming to potentially reduce accidents, and allow safe operation in dynamic attack surfaces, for the benefit of a host of stakeholders. This paper aims to bridge cybersecurity, safety, and privacy concerns in Connected and Autonomous Vehicles (CAV) with respect to Risk Assessment (RA) and Threat Modelling (TM) altogether. Practitioners know the vast literature on this topic given the sheer number of recommendations, standards, best practices, and existing approaches, at times impairing projects and fostering valuable and actionable threat analysis. In this paper we collate key outcomes by highlighting latest standards and approaches in RA and TM research to tackle complex attack surfaces as the ones posed by automotive settings. We aim to provide the community with a list of approaches to align expectations with stakeholders when deciding where and when to focus threat related analysis in automotive solutions.

Related papers

• SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator [77.86600052899156]
  Large Language Model (LLM)-based agents are increasingly deployed in real-world applications.<n>We propose AutoSafe, the first framework that systematically enhances agent safety through fully automated synthetic data generation.<n>We show that AutoSafe boosts safety scores by 45% on average and achieves a 28.91% improvement on real-world tasks.
  arXiv  Detail & Related papers  (2025-05-23T10:56:06Z)
• Cybersecurity for Autonomous Vehicles [0.0]
  The increasing adoption of autonomous vehicles is bringing a major shift in the automotive industry.<n>As these vehicles become more connected, cybersecurity threats have emerged as a serious concern.<n>This paper discusses major cybersecurity challenges like vulnerabilities in software and hardware, risks from wireless communication, and threats through external interfaces.
  arXiv  Detail & Related papers  (2025-04-28T18:31:37Z)
• Towards Zero Trust Security in Connected Vehicles: A Comprehensive Survey [0.27309692684728615]
  Zero Trust is the new cybersecurity model that challenges the traditional one by promoting continuous verification of users, devices, and applications.<n>This paper offers an understanding of Zero Trust security through a comprehensive review of existing literature, principles, and challenges.<n>Future directions of this research will focus on incorporating Zero Trust principles within Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communication paradigms.
  arXiv  Detail & Related papers  (2025-04-07T20:29:11Z)
• Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety [296.5392512998251]
  We present a comprehensive taxonomy of safety threats to large models, including adversarial attacks, data poisoning, backdoor attacks, jailbreak and prompt injection attacks, energy-latency attacks, data and model extraction attacks, and emerging agent-specific threats.<n>We identify and discuss the open challenges in large model safety, emphasizing the need for comprehensive safety evaluations, scalable and effective defense mechanisms, and sustainable data practices.
  arXiv  Detail & Related papers  (2025-02-02T05:14:22Z)
• Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving [65.61999354218628]
  We take the first step toward designing black-box adversarial attacks specifically targeting vision-language models (VLMs) in autonomous driving systems.<n>We propose Cascading Adversarial Disruption (CAD), which targets low-level reasoning breakdown by generating and injecting semantics.<n>We present Risky Scene Induction, which addresses dynamic adaptation by leveraging a surrogate VLM to understand and construct high-level risky scenarios.
  arXiv  Detail & Related papers  (2025-01-23T11:10:02Z)
• Open Problems in Machine Unlearning for AI Safety [61.43515658834902]
  Machine unlearning -- the ability to selectively forget or suppress specific types of knowledge -- has shown promise for privacy and data removal tasks.<n>In this paper, we identify key limitations that prevent unlearning from serving as a comprehensive solution for AI safety.
  arXiv  Detail & Related papers  (2025-01-09T03:59:10Z)
• Contextualizing Security and Privacy of Software-Defined Vehicles: State of the Art and Industry Perspectives [7.160802183553593]
  Survey explores the cybersecurity and privacy challenges posed by Software-Defined Vehicles (SDVs)<n>SDVs increasingly integrate features like Over-the-Air (OTA) updates and Vehicle-to-Everything (V2X) communication.<n>Transition to SDVs also raises significant privacy concerns, with vehicles collecting vast amounts of sensitive data.
  arXiv  Detail & Related papers  (2024-11-15T22:30:07Z)
• Enhancing Enterprise Security with Zero Trust Architecture [0.0]
  Zero Trust Architecture (ZTA) represents a transformative approach to modern cybersecurity. ZTA shifts the security paradigm by assuming that no user, device, or system can be trusted by default. This paper explores the key components of ZTA, such as identity and access management (IAM), micro-segmentation, continuous monitoring, and behavioral analytics.
  arXiv  Detail & Related papers  (2024-10-23T21:53:16Z)
• Securing Tomorrow's Smart Cities: Investigating Software Security in Internet of Vehicles and Deep Learning Technologies [1.0377683220196872]
  Integrating Deep Learning (DL) techniques in the Internet of Vehicles (IoV) introduces many security challenges and issues that require thorough examination. This literature review delves into the inherent vulnerabilities and risks associated with DL in IoV systems, shedding light on the multifaceted nature of security threats.
  arXiv  Detail & Related papers  (2024-07-23T11:56:33Z)
• Work-in-Progress: Crash Course: Can (Under Attack) Autonomous Driving Beat Human Drivers? [60.51287814584477]
  This paper evaluates the inherent risks in autonomous driving by examining the current landscape of AVs. We develop specific claims highlighting the delicate balance between the advantages of AVs and potential security challenges in real-world scenarios.
  arXiv  Detail & Related papers  (2024-05-14T09:42:21Z)
• A Counterfactual Safety Margin Perspective on the Scoring of Autonomous Vehicles' Riskiness [52.27309191283943]
  This paper presents a data-driven framework for assessing the risk of different AVs' behaviors. We propose the notion of counterfactual safety margin, which represents the minimum deviation from nominal behavior that could cause a collision.
  arXiv  Detail & Related papers  (2023-08-02T09:48:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.