A Human-in-the-Middle Attack against Object Detection Systems
Not on the map. Why?
Abstract (arXiv)
Object detection systems using deep learning models have become increasingly popular in robotics thanks to the rising power of CPUs and GPUs in embedded systems. However, these models are susceptible to adversarial attacks. While some attacks are limited by strict assumptions on access to the detection system, 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 via a hardware attack. Besides, prior research is misled by an evaluation metric that measures the model accuracy rather than the attack performance. In combination with our proposed evaluation metrics, we significantly increased the strength of adversarial perturbations. These findings raise serious concerns for applications of deep learning models in safety-critical systems, such as autonomous driving.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 29 of its 42 references that are in the map. First posted on arXiv 15 Aug 2022.
Builds on
29 of 42 references.
References · 29
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Mask R-CNNcited by 7,277
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2013Intriguing properties of neural networkscited by 5,155
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
- 2015SSD: Single Shot MultiBox Detectorcited by 3,130
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2018YOLOv3: An Incremental Improvementcited by 2,659
- 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
- 2017Evasion Attacks against Machine Learning at Test Timecited by 689
- 2018Object Detection with Deep Learning: A Reviewcited by 528
17 more
- 2017Soft-NMS -- Improving Object Detection With One Line of Codecited by 382
- 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
- 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
- 2021Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical Worldcited by 127
- 2018Transferable Adversarial Attacks for Image and Video Object Detectioncited by 109
- 2022Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenoncited by 101
- 2019On Physical Adversarial Patches for Object Detectioncited by 93
- 2021FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attackcited by 74
- 2017NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehiclescited by 48
- 2021Optical Adversarial Attackcited by 43
- 2021KITTI-CARLA: a KITTI-like dataset generated by CARLA Simulatorcited by 34
- 2017Adversarial Examples for Semantic Image Segmentationcited by 33
- 2019Man-in-the-Middle Attacks against Machine Learning Classifiers via Malicious Generative Modelscited by 19
- 2021Adversarial Driving: Attacking End-to-End Autonomous Drivingcited by 19
- 2020Transferable Universal Adversarial Perturbations Using Generative Modelscited by 10
- 2021Transferable Adversarial Examples for Anchor Free Object Detectioncited by 3
- 2018Traits & Transferability of Adversarial Examples against Instance Segmentation & Object Detectioncited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.