# Understanding Impacts of Electromagnetic Signal Injection Attacks on Object Detection

arXiv: https://arxiv.org/abs/2407.16327 · HTML: https://mlsanity.com/paper/2407.16327/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 35 references that are in the map.
- First posted on arXiv 23 Jul 2024.

## Builds on (most cited first, 14 of 14)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Object Detection in 20 Years: A Survey](https://mlsanity.com/paper/1905.05055/) (2019)
- [DETRs with Collaborative Hybrid Assignments Training](https://mlsanity.com/paper/2211.12860/) (2022)
- [COCO: A Platform for Comparing Continuous Optimizers in a Black-Box Setting](https://mlsanity.com/paper/1603.08785/) (2016)
- [Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles](https://mlsanity.com/paper/2003.08757/) (2020)
- [Invisible Perturbations: Physical Adversarial Examples Exploiting the Rolling Shutter Effect](https://mlsanity.com/paper/2011.13375/) (2020)
- [TPatch: A Triggered Physical Adversarial Patch](https://mlsanity.com/paper/2401.00148/) (2023)
- [They See Me Rollin': Inherent Vulnerability of the Rolling Shutter in CMOS Image Sensors](https://mlsanity.com/paper/2101.10011/) (2021)
- [Rolling Colors: Adversarial Laser Exploits against Traffic Light Recognition](https://mlsanity.com/paper/2204.02675/) (2022)
- [COCO: Performance Assessment](https://mlsanity.com/paper/1605.03560/) (2016)
- [Signal Injection Attacks against CCD Image Sensors](https://mlsanity.com/paper/2108.08881/) (2021)
- [Brokenwire : Wireless Disruption of CCS Electric Vehicle Charging](https://mlsanity.com/paper/2202.02104/) (2022)
- [Electromagnetic Signal Injection Attacks on Differential Signaling](https://mlsanity.com/paper/2208.00343/) (2022)

## Built on by (most cited first, 5 of 5)

- [Safety of Embodied Navigation: A Survey](https://mlsanity.com/paper/2508.05855/) (2025)
- [Is Your Autonomous Vehicle Safe? Understanding the Threat of Electromagnetic Signal Injection Attacks on Traffic Scene Perception](https://mlsanity.com/paper/2501.05239/) (2025)
- [A Simulation Framework for Electromagnetic Signal Injection Attacks on Image Sensors](https://mlsanity.com/paper/2408.05124/) (2024)
- [Rainbow Artifacts from Electromagnetic Signal Injection Attacks on Image Sensors](https://mlsanity.com/paper/2507.07773/) (2025)
- [See No Evil: Adversarial Attacks Against Linguistic-Visual Association in Referring Multi-Object Tracking Systems](https://mlsanity.com/paper/2509.02028/) (2025)

## Abstract (arXiv)

Object detection can localize and identify objects in images, and it is extensively employed in critical multimedia applications such as security surveillance and autonomous driving. Despite the success of existing object detection models, they are often evaluated in ideal scenarios where captured images guarantee the accurate and complete representation of the detecting scenes. However, images captured by image sensors may be affected by different factors in real applications, including cyber-physical attacks. In particular, attackers can exploit hardware properties within the systems to inject electromagnetic interference so as to manipulate the images. Such attacks can cause noisy or incomplete information about the captured scene, leading to incorrect detection results, potentially granting attackers malicious control over critical functions of the systems. This paper presents a research work that comprehensively quantifies and analyzes the impacts of such attacks on state-of-the-art object detection models in practice. It also sheds light on the underlying reasons for the incorrect detection outcomes.