mlsanityData to 7 Oct 2026

Fooling Object Detectors: Adversarial Attacks by Half-Neighbor Masks

arXiv 2101.00989 ↗First posted 4 Jan 2021cs.CV cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Although there are a great number of adversarial attacks on deep learning based classifiers, how to attack object detection systems has been rarely studied. In this paper, we propose a Half-Neighbor Masked Projected Gradient Descent (HNM-PGD) based attack, which can generate strong perturbation to fool different kinds of detectors under strict constraints. We also applied the proposed HNM-PGD attack in the CIKM 2020 AnalytiCup Competition, which was ranked within the top 1% on the leaderboard. We release the code at https://github.com/YanghaoZYH/HNM-PGD.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 12 of its 18 references that are in the map. First posted on arXiv 4 Jan 2021.

Builds on

12 of 18 references.

References · 12

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  6. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  7. 2018Reachability Analysis of Deep Neural Networks with Provable Guaranteescited by 93
  8. 2017Adversarial Examples that Fool Detectorscited by 39
  9. 2018A Game-Based Approximate Verification of Deep Neural Networks with Provable Guaranteescited by 33
  10. 2020Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible Noisescited by 32
  11. 2020Generalizing Universal Adversarial Attacks Beyond Additive Perturbationscited by 17
  12. 2018Collaboratively Weighting Deep and Classic Representation via L2 Regularization for Image Classificationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 0; 2023: 1; 2024: 1; 2025: 0; 2026: 1.

5 papers.

  1. 2021Sparse Adversarial Video Attacks with Spatial Transformationscited by 11
  2. 2024Towards Fairness-Aware Adversarial Learningcited by 10
  3. 2021Adversarial Robustness of Deep Learning: Theory, Algorithms, and Applicationscited by 5
  4. 2023A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarkingcited by 5
  5. 2026IoUCert: Robustness Verification for Anchor-based Object Detectorscited by 1