# TOG: Targeted Adversarial Objectness Gradient Attacks on Real-time Object Detection Systems

arXiv: https://arxiv.org/abs/2004.04320 · HTML: https://mlsanity.com/paper/2004.04320/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2020.

## Built on by (most cited first, 7 of 7)

- [A Review of Adversarial Attacks in Computer Vision](https://mlsanity.com/paper/2308.07673/) (2023)
- [VerifIoU -- Robustness of Object Detection to Perturbations](https://mlsanity.com/paper/2403.08788/) (2024)
- [Network transferability of adversarial patches in real-time object detection](https://mlsanity.com/paper/2408.15833/) (2024)
- [Fool the Stoplight: Realistic Adversarial Patch Attacks on Traffic Light Detectors](https://mlsanity.com/paper/2506.04823/) (2025)
- [In-the-Wild Camouflage Attack on Vehicle Detectors through Controllable Image Editing](https://mlsanity.com/paper/2603.19456/) (2026)
- [Fluently Lying: Adversarial Robustness Can Be Substrate-Dependent](https://mlsanity.com/paper/2604.00605/) (2026)
- [Localisation-Aware Uncertainty for Pretrained Object Detection](https://mlsanity.com/paper/2610.01409/) (2026)

## Abstract (arXiv)

The rapid growth of real-time huge data capturing has pushed the deep learning and data analytic computing to the edge systems. Real-time object recognition on the edge is one of the representative deep neural network (DNN) powered edge systems for real-world mission-critical applications, such as autonomous driving and augmented reality. While DNN powered object detection edge systems celebrate many life-enriching opportunities, they also open doors for misuse and abuse. This paper presents three Targeted adversarial Objectness Gradient attacks, coined as TOG, which can cause the state-of-the-art deep object detection networks to suffer from object-vanishing, object-fabrication, and object-mislabeling attacks. We also present a universal objectness gradient attack to use adversarial transferability for black-box attacks, which is effective on any inputs with negligible attack time cost, low human perceptibility, and particularly detrimental to object detection edge systems. We report our experimental measurements using two benchmark datasets (PASCAL VOC and MS COCO) on two state-of-the-art detection algorithms (YOLO and SSD). The results demonstrate serious adversarial vulnerabilities and the compelling need for developing robust object detection systems.