Steal Now and Attack Later: Evaluating Robustness of Object Detection against Black-box Adversarial Attacks
Not on the map. Why?
Abstract (arXiv)
Latency attacks against object detection represent a variant of adversarial attacks that aim to inflate the inference time by generating additional ghost objects in a target image. However, generating ghost objects in the black-box scenario remains a challenge since information about these unqualified objects remains opaque. In this study, we demonstrate the feasibility of generating ghost objects in adversarial examples by extending the concept of "steal now, decrypt later" attacks. These adversarial examples, once produced, can be employed to exploit potential vulnerabilities in the AI service, giving rise to significant security concerns. The experimental results demonstrate that the proposed attack achieves successful attacks across various commonly used models and Google Vision API without any prior knowledge about the target model. Additionally, the average cost of each attack is less than 1 dollars, posing a significant threat to AI security.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 29 of its 45 references that are in the map. First posted on arXiv 24 Apr 2024.
Builds on
29 of 45 references.
References · 29
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
- 2020End-to-End Object Detection with Transformerscited by 7,414
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2015SSD: Single Shot MultiBox Detectorcited by 3,130
- 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
- 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
- 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
- 2017One pixel attack for fooling deep neural networkscited by 582
- 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
- 2016Speed/accuracy trade-offs for modern convolutional object detectorscited by 198
17 more
- 2023StableVideo: Text-driven Consistency-aware Diffusion Video Editingcited by 183
- 2019Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectorscited by 155
- 2018Query-Efficient Hard-label Black-box Attack:An Optimization-based Approachcited by 130
- 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 98
- 2022Adversarial Texture for Fooling Person Detectors in the Physical Worldcited by 96
- 2020Toward Transformer-Based Object Detectioncited by 84
- 2022Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detectioncited by 79
- 2022A Large-scale Multiple-objective Method for Black-box Attack against Object Detectioncited by 55
- 2019Fooling a Real Car with Adversarial Traffic Signscited by 29
- 2022Phantom Sponges: Exploiting Non-Maximum Suppression to Attack Deep Object Detectorscited by 28
- 2019A Review of Object Detection Models based on Convolutional Neural Networkcited by 22
- 2021Context-Aware Transfer Attacks for Object Detectioncited by 18
- 2022Zero-Query Transfer Attacks on Context-Aware Object Detectorscited by 17
- 2020Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistencycited by 16
- 2021Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box Attackscited by 16
- 2023SlowTrack: Increasing the Latency of Camera-based Perception in Autonomous Driving Using Adversarial Examplescited by 15
- 2023Overload: Latency Attacks on Object Detection for Edge Devicescited by 13
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 1.
2 papers.