Skip to content
AI News HubLIVE
Original source2 min read

Adversarial Tracking: Attacks on Image Sensors for Object Tracking in Autonomous Vehicles

Summary

This paper evaluates image-specific and image-agnostic adversarial attacks on YOLOv3/YOLOv4 detectors paired with SORT, Deep SORT, Strong SORT, and OC-SORT trackers in the CARLA simulator. Image-specific attacks drop HOTA for YOLOv3-based trackers from 53.45-56.19% to 14.85-17.03%, with MOTA reaching -772.60% in the worst case. YOLOv4-based trackers are more robust but HOTA still falls to 25.06-26.86%. Image-agnostic attacks using a single Universal Adversarial Perturbation (UAP) can also degrade tracking accuracy without per-frame perturbations.

SourcearXiv Computer VisionAuthor: Han Wu, Alex Chan, Ekin Can Erkus, Tousif Rahman, Rishad Shafik
Adversarial Tracking: Attacks on Image Sensors for Object Tracking in Autonomous Vehicles
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 12 Nov 2026]

Title:Adversarial Tracking: Attacks on Image Sensors for Object Tracking in Autonomous Vehicles

View a PDF of the paper titled Adversarial Tracking: Attacks on Image Sensors for Object Tracking in Autonomous Vehicles, by Han Wu and 3 other authors

View PDF HTML (experimental)

Abstract:Object tracking systems estimate the motion of surrounding vehicles by linking detected objects across video frames. In particular, Tracking-By-Detection (TBD) systems combine object detectors with motion prediction and data association to maintain object identities over time. However, neural network-based detectors are vulnerable to adversarial attacks that perturb input images, and their impact on downstream trajectory estimation is not fully characterized by detection accuracy alone. Therefore, this paper evaluates image-specific and image-agnostic attacks on YOLOv3 and YOLOv4 detectors paired with SORT, Deep SORT, Strong SORT, and OC-SORT tracking systems. The evaluation uses CARLA simulator and measures tracking quality through Multiple Object Tracking Accuracy (MOTA), Higher Order Tracking Accuracy (HOTA), and Identification F1 (IDF1). Under image-specific attacks, HOTA for YOLOv3-based trackers declines from 53.45-56.19% to 14.85-17.03%, while MOTA reaches -772.60% in the worst case. YOLOv4-based trackers exhibit greater robustness, while HOTA still declines to 25.06-26.86%. In addition, image-agnostic attacks can reduce the tracking accuracy using a single Universal Adversarial Perturbation (UAP), without generating a separate perturbation for individual frames.

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)

Cite as: arXiv:2611.17505 [cs.CV]

(or arXiv:2611.17505v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2611.17505

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Han Wu [view email] [v1] Thu, 12 Nov 2026 20:56:53 UTC (3,699 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Adversarial Tracking: Attacks on Image Sensors for Object Tracking in Autonomous Vehicles, by Han Wu and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CV

new | recent | 2026-11

Change to browse by:

cs cs.AI

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • Evaluates image-specific and image-agnostic attacks on YOLOv3/YOLOv4 paired with four SORT-family trackers.
  • Image-specific attacks drop HOTA for YOLOv3 trackers from ~55% to ~16%, with worst MOTA at -772.60%.
  • YOLOv4-based trackers show greater robustness, but HOTA still declines to 25.06-26.86%.
  • A single Universal Adversarial Perturbation (UAP) enables image-agnostic attacks that reduce tracking accuracy.

Highlights and analysis are generated automatically and may contain errors. Check the original source.