mlsanityData to 14 Oct 2026

Preventing Adversarial AI Attacks Against Autonomous Situational Awareness: A Maritime Case Study

arXiv 2505.21609 ↗First posted 27 May 2025cs.CR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Adversarial artificial intelligence (AI) attacks pose a significant threat to autonomous transportation, such as maritime vessels, that rely on AI components. Malicious actors can exploit these systems to deceive and manipulate AI-driven operations. This paper addresses three critical research challenges associated with adversarial AI: the limited scope of traditional defences, inadequate security metrics, and the need to build resilience beyond model-level defences. To address these challenges, we propose building defences utilising multiple inputs and data fusion to create defensive components and an AI security metric as a novel approach toward developing more secure AI systems. We name this approach the Data Fusion Cyber Resilience (DFCR) method, and we evaluate it through real-world demonstrations and comprehensive quantitative analyses, comparing a system built with the DFCR method against single-input models and models utilising existing state-of-the-art defences. The findings show that the DFCR approach significantly enhances resilience against adversarial machine learning attacks in maritime autonomous system operations, achieving up to a 35% reduction in loss for successful multi-pronged perturbation attacks, up to a 100% reduction in loss for successful adversarial patch attacks and up to 100% reduction in loss for successful spoofing attacks when using these more resilient systems. We demonstrate how DFCR and DFCR confidence scores can reduce adversarial AI contact confidence and improve decision-making by the system, even when typical adversarial defences have been compromised. Ultimately, this work contributes to the development of more secure and resilient AI-driven systems against adversarial attacks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 88 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

31 of 88 references.

References · 31

  1. 2020End-to-End Object Detection with Transformerscited by 7,414
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  6. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  7. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  8. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  9. 2016Adversarial Machine Learning at Scalecited by 936
  10. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  11. 2017Evasion Attacks against Machine Learning at Test Timecited by 689
  12. 2016Stealing Machine Learning Models via Prediction APIscited by 619
19 more
  1. 2017One pixel attack for fooling deep neural networkscited by 582
  2. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 387
  3. 2021Understanding Robustness of Transformers for Image Classificationcited by 249
  4. 2016A study of the effect of JPG compression on adversarial imagescited by 197
  5. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attackscited by 194
  6. 2013Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifierscited by 130
  7. 2021Towards Transferable Adversarial Attacks on Vision Transformerscited by 80
  8. 2022Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?cited by 49
  9. 2024Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Modelscited by 44
  10. 2021Reveal of Vision Transformers Robustness against Adversarial Attackscited by 43
  11. 2019Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and The Way Forwardcited by 33
  12. 2022Machine Learning Security in Industry: A Quantitative Surveycited by 21
  13. 2018Attack Strength vs. Detectability Dilemma in Adversarial Machine Learningcited by 14
  14. 2023Asynchronous Trajectory Matching-Based Multimodal Maritime Data Fusion for Vessel Traffic Surveillance in Inland Waterwayscited by 13
  15. 2020Space-based Global Maritime Surveillance. Part II: Artificial Intelligence and Data Fusion Techniquescited by 6
  16. 2023Image and AIS Data Fusion Technique for Maritime Computer Vision Applicationscited by 5
  17. 2023SlowFormer: Universal Adversarial Patch for Attack on Compute and Energy Efficiency of Inference Efficient Vision Transformerscited by 3
  18. 2023A Red Teaming Framework for Securing AI in Maritime Autonomous Systemscited by 3
  19. 2024DeSparsify: Adversarial Attack Against Token Sparsification Mechanisms in Vision Transformerscited by 2

Built on by

Not cited yet.