mlsanityData to 7 Oct 2026

Enhancing Object Detection Robustness: Detecting and Restoring Confidence in the Presence of Adversarial Patch Attacks

arXiv 2403.12988 ↗First posted 4 Mar 2024cs.CV cs.AIcited by 2

On the map: Diffusion models → Robustness, privacy and adversarial aspects

Abstract (arXiv)

The widespread adoption of computer vision systems has underscored their susceptibility to adversarial attacks, particularly adversarial patch attacks on object detectors. This study evaluates defense mechanisms for the YOLOv5 model against such attacks. Optimized adversarial patches were generated and placed in sensitive image regions, by applying EigenCAM and grid search to determine optimal placement. We tested several defenses, including Segment and Complete (SAC), Inpainting, and Latent Diffusion Models. Our pipeline comprises three main stages: patch application, object detection, and defense analysis. Results indicate that adversarial patches reduce average detection confidence by 22.06%. Defenses restored confidence levels by 3.45% (SAC), 5.05% (Inpainting), and significantly improved them by 26.61%, which even exceeds the original accuracy levels, when using the Latent Diffusion Model, highlighting its superior effectiveness in mitigating the effects of adversarial patches.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 12 of its 29 references that are in the map. First posted on arXiv 4 Mar 2024.

Builds on

12 of 29 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Diffusion to Confusion: Naturalistic Adversarial Patch Generation Based on Diffusion Model for Object Detector16 Jul

Other references · 11

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  3. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  4. 2016Tutorial on Variational Autoencoderscited by 404
  5. 2020Eigen-CAM: Class Activation Map using Principal Componentscited by 188
  6. 2021Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detectioncited by 67
  7. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 66
  8. 2023Patch of Invisibility: Naturalistic Physical Black-Box Adversarial Attacks on Object Detectorscited by 5
  9. 2023MVPatch: More Vivid Patch for Adversarial Camouflaged Attacks on Object Detectors in the Physical Worldcited by 4
  10. 2023Detection of Uncertainty in Exceedance of Threshold (DUET): An Adversarial Patch Localizercited by 2
  11. 2023Architecture-agnostic Iterative Black-box Certified Defense against Adversarial Patchescited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Seeing Isn't Believing: Context-Aware Adversarial Patch Synthesis via Conditional GANcited by 2
  2. 2026Learning What to Fail On: Failure-Mode Contextual Bandits for Adversarial Data Curationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A Survey and Evaluation of Adversarial Attacks for Object Detection
  2. 2024AdvLogo: Adversarial Patch Attack against Object Detectors based on Diffusion Models
  3. 2025DisPatch: Disarming Adversarial Patches in Object Detection with Diffusion Models
  4. 2023DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks
  5. 2024Real-world Adversarial Defense against Patch Attacks based on Diffusion Model
  6. 2025Don't Lag, RAG: Training-Free Adversarial Detection Using RAG
  7. 2024DiffPAD: Denoising Diffusion-based Adversarial Patch Decontamination
  8. 2024Prompt-Guided Environmentally Consistent Adversarial Patch