mlsanityData to 13 Oct 2026

Indirect Local Attacks for Context-aware Semantic Segmentation Networks

arXiv 1911.13038 ↗First posted 29 Nov 2019cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

Recently, deep networks have achieved impressive semantic segmentation performance, in particular thanks to their use of larger contextual information. In this paper, we show that the resulting networks are sensitive not only to global attacks, where perturbations affect the entire input image, but also to indirect local attacks where perturbations are confined to a small image region that does not overlap with the area that we aim to fool. To this end, we introduce several indirect attack strategies, including adaptive local attacks, aiming to find the best image location to perturb, and universal local attacks. Furthermore, we propose attack detection techniques both for the global image level and to obtain a pixel-wise localization of the fooled regions. Our results are unsettling: Because they exploit a larger context, more accurate semantic segmentation networks are more sensitive to indirect local attacks.

Key facts. Cited by 23 papers in the map (data through 13 Oct 2026). First posted on arXiv 29 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 5; 2022: 8; 2023: 3; 2024: 4; 2025: 2; 2026: 1.

23 papers.

Sort:

  1. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  2. 2022SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustnesscited by 74
  3. 2021Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attackscited by 55
  4. 2022On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Drivingcited by 30
  5. 2022A Survey on Physical Adversarial Attack in Computer Visioncited by 24
  6. 2022SoK: On the Semantic AI Security in Autonomous Drivingcited by 22
  7. 2022GAMA: Generative Adversarial Multi-Object Scene Attackscited by 13
  8. 2022Defending From Physically-Realizable Adversarial Attacks Through Internal Over-Activation Analysiscited by 10
  9. 2023Uncertainty-weighted Loss Functions for Improved Adversarial Attacks on Semantic Segmentationcited by 9
  10. 2022Leveraging Local Patch Differences in Multi-Object Scenes for Generative Adversarial Attackscited by 5
  11. 2023Uncertainty-based Detection of Adversarial Attacks in Semantic Segmentationcited by 5
  12. 2021On Adversarial Robustness of Point Cloud Semantic Segmentationcited by 3
11 more
  1. 2023Fooling the Image Dehazing Models by First Order Gradientcited by 3
  2. 2025Benchmarking the Spatial Robustness of DNNs via Natural and Adversarial Localized Corruptionscited by 3
  3. 2024Towards Robust Semantic Segmentation against Patch-based Attack via Attention Refinementcited by 2
  4. 2024Edge-Only Universal Adversarial Attacks in Distributed Learningcited by 2
  5. 2022On the Feasibility and Generality of Patch-based Adversarial Attacks on Semantic Segmentation Problemscited by 1
  6. 2024Delving into Decision-based Black-box Attacks on Semantic Segmentationcited by 1
  7. 2024Detecting Adversarial Attacks in Semantic Segmentation via Uncertainty Estimation: A Deep Analysiscited by 1
  8. 2025NAT: Learning to Attack Neurons for Enhanced Adversarial Transferabilitycited by 1
  9. 2021DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flowscited by 0
  10. 2021Associative Adversarial Learning Based on Selective Attackcited by 0
  11. 2026Learning with Bilevel-Minimax Optimization for Efficient and Reliable Transfer Attackscited by 0