# Understanding Object Detection Through An Adversarial Lens

arXiv: https://arxiv.org/abs/2007.05828 · HTML: https://mlsanity.com/paper/2007.05828/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jul 2020.

## Built on by (most cited first, 10 of 10)

- [Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance](https://mlsanity.com/paper/2402.01096/) (2024)
- [Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control](https://mlsanity.com/paper/2401.01085/) (2024)
- [A Survey and Evaluation of Adversarial Attacks for Object Detection](https://mlsanity.com/paper/2408.01934/) (2024)
- [Exploring Model Learning Heterogeneity for Boosting Ensemble Robustness](https://mlsanity.com/paper/2310.02237/) (2023)
- [PapMOT: Exploring Adversarial Patch Attack against Multiple Object Tracking](https://mlsanity.com/paper/2504.09361/) (2025)
- [Adversarial Attention Perturbations for Large Object Detection Transformers](https://mlsanity.com/paper/2508.02987/) (2025)
- [AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection](https://mlsanity.com/paper/2503.06529/) (2025)
- [Using Frequency Attention to Make Adversarial Patch Powerful Against Person Detector](https://mlsanity.com/paper/2205.04638/) (2022)
- [On Feasibility of Intent Obfuscating Attacks](https://mlsanity.com/paper/2408.02674/) (2024)
- [AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection](https://mlsanity.com/paper/2411.14243/) (2024)

## Abstract (arXiv)

Deep neural networks based object detection models have revolutionized computer vision and fueled the development of a wide range of visual recognition applications. However, recent studies have revealed that deep object detectors can be compromised under adversarial attacks, causing a victim detector to detect no object, fake objects, or mislabeled objects. With object detection being used pervasively in many security-critical applications, such as autonomous vehicles and smart cities, we argue that a holistic approach for an in-depth understanding of adversarial attacks and vulnerabilities of deep object detection systems is of utmost importance for the research community to develop robust defense mechanisms. This paper presents a framework for analyzing and evaluating vulnerabilities of the state-of-the-art object detectors under an adversarial lens, aiming to analyze and demystify the attack strategies, adverse effects, and costs, as well as the cross-model and cross-resolution transferability of attacks. Using a set of quantitative metrics, extensive experiments are performed on six representative deep object detectors from three popular families (YOLOv3, SSD, and Faster R-CNN) with two benchmark datasets (PASCAL VOC and MS COCO). We demonstrate that the proposed framework can serve as a methodical benchmark for analyzing adversarial behaviors and risks in real-time object detection systems. We conjecture that this framework can also serve as a tool to assess the security risks and the adversarial robustness of deep object detectors to be deployed in real-world applications.