Testing autonomous vehicles and AI: perspectives and challenges from cybersecurity, transparency, robustness and fairness

arXiv 2403.14641 ↗First posted 21 Feb 2024cs.CY cs.AI cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

This study explores the complexities of integrating Artificial Intelligence (AI) into Autonomous Vehicles (AVs), examining the challenges introduced by AI components and the impact on testing procedures, focusing on some of the essential requirements for trustworthy AI. Topics addressed include the role of AI at various operational layers of AVs, the implications of the EU's AI Act on AVs, and the need for new testing methodologies for Advanced Driver Assistance Systems (ADAS) and Automated Driving Systems (ADS). The study also provides a detailed analysis on the importance of cybersecurity audits, the need for explainability in AI decision-making processes and protocols for assessing the robustness and ethical behaviour of predictive systems in AVs. The paper identifies significant challenges and suggests future directions for research and development of AI in AV technology, highlighting the need for multidisciplinary expertise.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 90 of its 178 references that are in the map. First posted on arXiv 21 Feb 2024.

Builds on

90 of 178 references.

References · 90

2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
2017Axiomatic Attribution for Deep Networkscited by 3,350
2015Learning Deep Features for Discriminative Localizationcited by 2,430
2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
2016Adversarial examples in the physical worldcited by 1,762
2017Learning Important Features Through Propagating Activation Differencescited by 1,454
2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
2016Stealing Machine Learning Models via Prediction APIscited by 602

38 more

2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
2019On Evaluating Adversarial Robustnesscited by 442
2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 403
2020Learning Lane Graph Representations for Motion Forecastingcited by 380
2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 359
2020Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Surveycited by 252
2016A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehiclescited by 251
2020One Thousand and One Hours: Self-driving Motion Prediction Datasetcited by 239
2018Textual Explanations for Self-Driving Vehiclescited by 226
2018Adversarial Robustness Toolbox v1.0.0cited by 214
2017Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimizationcited by 188
2017Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Artcited by 182
2020Physically Realizable Adversarial Examples for LiDAR Object Detectioncited by 137
2020Human Trajectory Forecasting in Crowds: A Deep Learning Perspectivecited by 128
2022BackdoorBench: A Comprehensive Benchmark of Backdoor Learningcited by 124
2016Technical Report on the CleverHans v2.1.0 Adversarial Examples Librarycited by 123
2019Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Modelscited by 118
2018Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoningcited by 102
2020Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehiclescited by 101
2020Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Databasecited by 95
2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
2020Explainable Object-induced Action Decision for Autonomous Vehiclescited by 88
2020What-If Motion Prediction for Autonomous Drivingcited by 80
2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
2021Explanations in Autonomous Driving: A Surveycited by 80
2021ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Modelscited by 79
2019Predictive Inequity in Object Detectioncited by 77
2018Autonomous Vehicles that Interact with Pedestrians: A Survey of Theory and Practicecited by 74
2019Policy Poisoning in Batch Reinforcement Learning and Controlcited by 70
2019Bypassing Backdoor Detection Algorithms in Deep Learningcited by 69
2020Diverse and Admissible Trajectory Forecasting through Multimodal Context Understandingcited by 68
2020When Machine Learning Meets Privacy: A Survey and Outlookcited by 67
2015Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlocited by 61
2021A Backdoor Attack against 3D Point Cloud Classifierscited by 50
2018Scenarios for Development, Test and Validation of Automated Vehiclescited by 45
2020The Emerging Landscape of Explainable AI Planning and Decision Makingcited by 44
2020Hermes Attack: Steal DNN Models with Lossless Inference Accuracycited by 41

50 most cited of 90 All 90 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 2.

3 papers.