mlsanityData to 7 Oct 2026

Robust Adversarial Perturbation on Deep Proposal-based Models

arXiv 1809.05962 ↗First posted 16 Sep 2018cs.CVcited by 26

Not on the map. Why?

Abstract (arXiv)

Adversarial noises are useful tools to probe the weakness of deep learning based computer vision algorithms. In this paper, we describe a robust adversarial perturbation (R-AP) method to attack deep proposal-based object detectors and instance segmentation algorithms. Our method focuses on attacking the common component in these algorithms, namely Region Proposal Network (RPN), to universally degrade their performance in a black-box fashion. To do so, we design a loss function that combines a label loss and a novel shape loss, and optimize it with respect to image using a gradient based iterative algorithm. Evaluations are performed on the MS COCO 2014 dataset for the adversarial attacking of 6 state-of-the-art object detectors and 2 instance segmentation algorithms. Experimental results demonstrate the efficacy of the proposed method.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 4; 2023: 7; 2024: 4; 2025: 2; 2026: 3.

26 papers.

Sort:

By area:

  1. 2022Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detectioncited by 79
  2. 2022T-SEA: Transfer-based Self-Ensemble Attack on Object Detectioncited by 59
  3. 2021Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Drivingcited by 45
  4. 2021Class-Aware Robust Adversarial Training for Object Detectioncited by 27
  5. 2022Adversarial Attack and Defense of YOLO Detectors in Autonomous Driving Scenarioscited by 20
  6. 2021Context-Aware Transfer Attacks for Object Detectioncited by 18
  7. 2024NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectorscited by 17
  8. 2021Adversarial Feature Augmentation and Normalization for Visual Recognitioncited by 11
  9. 2023Diffusion to Confusion: Naturalistic Adversarial Patch Generation Based on Diffusion Model for Object Detectorcited by 10
  10. 2023Threatening Patch Attacks on Object Detection in Optical Remote Sensing Imagescited by 8
  11. 2021Integer-arithmetic-only Certified Robustness for Quantized Neural Networkscited by 7
  12. 2024A Survey and Evaluation of Adversarial Attacks for Object Detectioncited by 7
14 more
  1. 2023Exploring Model Learning Heterogeneity for Boosting Ensemble Robustnesscited by 6
  2. 2023A Review of Adversarial Attacks in Computer Visioncited by 5
  3. 2022General Adversarial Defense Against Black-box Attacks via Pixel Level and Feature Level Distribution Alignmentscited by 4
  4. 2025Adversarial Attention Perturbations for Large Object Detection Transformerscited by 4
  5. 2021Robust and Accurate Object Detection via Self-Knowledge Distillationcited by 3
  6. 2024Can't Slow me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devicescited by 3
  7. 2023AdvMono3D: Advanced Monocular 3D Object Detection with Depth-Aware Robust Adversarial Trainingcited by 2
  8. 2023GLOW: Global Layout Aware Attacks on Object Detectioncited by 1
  9. 2023Towards Generic and Controllable Attacks Against Object Detectioncited by 0
  10. 2024Adversarial Attacks on LiDAR-Based Tracking Across Road Users: Robustness Evaluation and Target-Aware Black-Box Methodcited by 0
  11. 2025Adversarial Patch Attack for Ship Detection via Localized Augmentationcited by 0
  12. 2026A Unified Spatial Alignment Framework for Highly Transferable Transformation-Based Attacks on Spatially Structured Taskscited by 0
  13. 2026LipSSD: Lipschitz-Constrained Single-Shot Detection for Adversarially Robust Object Detectioncited by 0
  14. 2026Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformerscited by 0