A Taxonomy of System-Level Attacks on Deep Learning Models in Autonomous Vehicles

• URL: http://arxiv.org/abs/2412.04510v1
• Date: Wed, 04 Dec 2024 09:49:55 GMT
• Title: A Taxonomy of System-Level Attacks on Deep Learning Models in Autonomous Vehicles
• Abstract summary: We present the first taxonomy of system-level attacks against autonomous vehicles.<n>We constructed our taxonomy by first collecting 8,831 papers, then filtering them down to 1,125 candidates.<n>The resulting taxonomy includes 12 top-level categories and several sub-categories.
• Score: 45.754302253504626
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The advent of deep learning and its astonishing performance in perception tasks, such as object recognition and classification, has enabled its usage in complex systems, including autonomous vehicles. On the other hand, deep learning models are susceptible to mis-predictions when small, adversarial changes are introduced into their input. Such mis-predictions can be triggered in the real world and can propagate to a failure of the entire system, as opposed to a localized mis-prediction. In recent years, a growing number of research works have investigated ways to mount attacks against autonomous vehicles that exploit deep learning components for perception tasks. Such attacks are directed toward elements of the environment where these systems operate and their effectiveness is assessed in terms of system-level failures triggered by them. There has been however no systematic attempt to analyze and categorize such attacks. In this paper, we present the first taxonomy of system-level attacks against autonomous vehicles. We constructed our taxonomy by first collecting 8,831 papers, then filtering them down to 1,125 candidates and eventually selecting a set of 19 highly relevant papers that satisfy all inclusion criteria. Then, we tagged them with taxonomy categories, involving three assessors per paper. The resulting taxonomy includes 12 top-level categories and several sub-categories. The taxonomy allowed us to investigate the attack features, the most attacked components, the underlying threat models, and the propagation chains from input perturbation to system-level failure. We distilled several lessons for practitioners and identified possible directions for future work for researchers.

Related papers

• Defending against adversarial attacks using mixture of experts [1.3578741464318356]
  Adversarial threats aim to hinder the machine learning models from satisfying their objectives.<n>We propose a defense system, which devises an adversarial training module within mixture-of-experts architecture.
  arXiv  Detail & Related papers  (2025-12-23T22:46:06Z)
• Evasion Attacks Against Bayesian Predictive Models [1.8570591025615457]
  This paper introduces a general methodology for designing optimal evasion attacks against such models.<n>We investigate two adversarial objectives: perturbing specific point predictions and altering the entire posterior predictive distribution.<n>For both scenarios, we propose novel gradient-based attacks and study their implementation and properties in various computational setups.
  arXiv  Detail & Related papers  (2025-06-11T11:53:20Z)
• Inference Attacks: A Taxonomy, Survey, and Promising Directions [44.290208239143126]
  This survey provides an in-depth and comprehensive inference of attacks and corresponding countermeasures in ML-as-a-service. We first propose the 3MP taxonomy based on the community research status, trying to normalize the confusing naming system of inference attacks. Also, we analyze the pros and cons of each type of inference attack, their workflow, countermeasure, and how they interact with other attacks.
  arXiv  Detail & Related papers  (2024-06-04T07:06:06Z)
• CANEDERLI: On The Impact of Adversarial Training and Transferability on CAN Intrusion Detection Systems [17.351539765989433]
  A growing integration of vehicles with external networks has led to a surge in attacks targeting their Controller Area Network (CAN) internal bus. As a countermeasure, various Intrusion Detection Systems (IDSs) have been suggested in the literature to prevent and mitigate these threats. Most of these systems rely on data-driven approaches such as Machine Learning (ML) and Deep Learning (DL) models. In this paper, we present CANEDERLI, a novel framework for securing CAN-based IDSs.
  arXiv  Detail & Related papers  (2024-04-06T14:54:11Z)
• Taxonomy for Cybersecurity Threat Attributes and Countermeasures in Smart Manufacturing Systems [0.0]
  Existing attack taxonomy only focus on a narrow range of attacks and limited threat attributes. This paper proposes a comprehensive attack taxonomy for a holistic understanding and characterization of cybersecurity threats in manufacturing systems.
  arXiv  Detail & Related papers  (2023-12-30T02:11:02Z)
• Ecosystem-level Analysis of Deployed Machine Learning Reveals Homogeneous Outcomes [72.13373216644021]
  We study the societal impact of machine learning by considering the collection of models that are deployed in a given context. We find deployed machine learning is prone to systemic failure, meaning some users are exclusively misclassified by all models available. These examples demonstrate ecosystem-level analysis has unique strengths for characterizing the societal impact of machine learning.
  arXiv  Detail & Related papers  (2023-07-12T01:11:52Z)
• When Authentication Is Not Enough: On the Security of Behavioral-Based Driver Authentication Systems [53.2306792009435]
  We develop two lightweight driver authentication systems based on Random Forest and Recurrent Neural Network architectures. We are the first to propose attacks against these systems by developing two novel evasion attacks, SMARTCAN and GANCAN. Through our contributions, we aid practitioners in safely adopting these systems, help reduce car thefts, and enhance driver security.
  arXiv  Detail & Related papers  (2023-06-09T14:33:26Z)
• Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective [69.25513235556635]
  Adversarial machine learning (AML) studies the adversarial phenomenon of machine learning, which may make inconsistent or unexpected predictions with humans. Some paradigms have been recently developed to explore this adversarial phenomenon occurring at different stages of a machine learning system. We propose a unified mathematical framework to covering existing attack paradigms.
  arXiv  Detail & Related papers  (2023-02-19T02:12:21Z)
• Hierarchical Classification of Research Fields in the "Web of Science" Using Deep Learning [15.915719490494876]
  This paper presents a hierarchical classification system that automatically categorizes a scholarly publication using its abstract. It distinguishes 44 disciplines, 718 fields and 1,485 subfields among 160 million abstract snippets in Microsoft Academic Graph. The classification accuracy is > 90% in 77.13% and 78.19% of the single-label and multi-label classifications, respectively.
  arXiv  Detail & Related papers  (2023-02-01T11:59:17Z)
• Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems [80.3811072650087]
  We show that it is possible to subtly modify claim-salient snippets in the evidence and generate diverse and claim-aligned evidence. The attacks are also robust against post-hoc modifications of the claim. These attacks can have harmful implications on the inspectable and human-in-the-loop usage scenarios.
  arXiv  Detail & Related papers  (2022-09-07T13:39:24Z)
• A Human-in-the-Middle Attack against Object Detection Systems [4.764637544913963]
  We propose a novel hardware attack inspired by Man-in-the-Middle attacks in cryptography. This attack generates a Universal Adversarial Perturbations (UAP) and injects the perturbation between the USB camera and the detection system. These findings raise serious concerns for applications of deep learning models in safety-critical systems, such as autonomous driving.
  arXiv  Detail & Related papers  (2022-08-15T13:21:41Z)
• Neurosymbolic hybrid approach to driver collision warning [64.02492460600905]
  There are two main algorithmic approaches to autonomous driving systems. Deep learning alone has achieved state-of-the-art results in many areas. But sometimes it can be very difficult to debug if the deep learning model doesn't work.
  arXiv  Detail & Related papers  (2022-03-28T20:29:50Z)
• Anomaly Detection in Cybersecurity: Unsupervised, Graph-Based and Supervised Learning Methods in Adversarial Environments [63.942632088208505]
  Inherent to today's operating environment is the practice of adversarial machine learning. In this work, we examine the feasibility of unsupervised learning and graph-based methods for anomaly detection. We incorporate a realistic adversarial training mechanism when training our supervised models to enable strong classification performance in adversarial environments.
  arXiv  Detail & Related papers  (2021-05-14T10:05:10Z)
• ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models [64.03398193325572]
  Inference attacks against Machine Learning (ML) models allow adversaries to learn about training data, model parameters, etc. We concentrate on four attacks - namely, membership inference, model inversion, attribute inference, and model stealing. Our analysis relies on a modular re-usable software, ML-Doctor, which enables ML model owners to assess the risks of deploying their models.
  arXiv  Detail & Related papers  (2021-02-04T11:35:13Z)
• Adversarial Attacks on Machine Learning Cybersecurity Defences in Industrial Control Systems [2.86989372262348]
  This paper explores how adversarial learning can be used to target supervised models by generating adversarial samples. It also explores how such samples can support the robustness of supervised models using adversarial training. Overall, the classification performance of two widely used classifiers, Random Forest and J48, decreased by 16 and 20 percentage points when adversarial samples were present.
  arXiv  Detail & Related papers  (2020-04-10T12:05:33Z)
• Adversarial Attacks on Machine Learning Systems for High-Frequency Trading [55.30403936506338]
  We study valuation models for algorithmic trading from the perspective of adversarial machine learning. We introduce new attacks specific to this domain with size constraints that minimize attack costs. We discuss how these attacks can be used as an analysis tool to study and evaluate the robustness properties of financial models.
  arXiv  Detail & Related papers  (2020-02-21T22:04:35Z)
• Enhanced Adversarial Strategically-Timed Attacks against Deep Reinforcement Learning [91.13113161754022]
  We introduce timing-based adversarial strategies against a DRL-based navigation system by jamming in physical noise patterns on the selected time frames. Our experimental results show that the adversarial timing attacks can lead to a significant performance drop.
  arXiv  Detail & Related papers  (2020-02-20T21:39:25Z)

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.