mlsanityData to 7 Oct 2026

Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation

arXiv 1810.05162 ↗First posted 11 Oct 2018cs.CR cs.CV cs.LGcited by 40

Not on the map. Why?

Abstract (arXiv)

Deep Neural Networks (DNNs) have been widely applied in various recognition tasks. However, recently DNNs have been shown to be vulnerable against adversarial examples, which can mislead DNNs to make arbitrary incorrect predictions. While adversarial examples are well studied in classification tasks, other learning problems may have different properties. For instance, semantic segmentation requires additional components such as dilated convolutions and multiscale processing. In this paper, we aim to characterize adversarial examples based on spatial context information in semantic segmentation. We observe that spatial consistency information can be potentially leveraged to detect adversarial examples robustly even when a strong adaptive attacker has access to the model and detection strategies. We also show that adversarial examples based on attacks considered within the paper barely transfer among models, even though transferability is common in classification. Our observations shed new light on developing adversarial attacks and defenses to better understand the vulnerabilities of DNNs.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 17; 2022: 9; 2023: 10; 2024: 3; 2025: 1.

40 papers.

Sort:

By area:

  1. 2021Unsolved Problems in ML Safetycited by 291
  2. 2021Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attackscited by 101
  3. 2022SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustnesscited by 74
  4. 2021End-to-end Prostate Cancer Detection in bpMRI via 3D CNNs: Effects of Attention Mechanisms, Clinical Priori and Decoupled False Positive Reductioncited by 32
  5. 2022LOT: Layer-wise Orthogonal Training on Improving ℓ2 Certified Robustnesscited by 32
  6. 2022Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loopcited by 30
  7. 2021Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformationscited by 28
  8. 2021Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attackscited by 24
  9. 2021Evaluating Adversarial Attacks on Driving Safety in Vision-Based Autonomous Vehiclescited by 24
  10. 2021Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuningcited by 24
  11. 2021Taxonomy of Machine Learning Safety: A Survey and Primercited by 22
  12. 2022Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networkscited by 18
28 more
  1. 2022PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognitioncited by 16
  2. 2021Adversarial Examples on Segmentation Models Can be Easy to Transfercited by 15
  3. 2021Exploiting Multi-Object Relationships for Detecting Adversarial Attacks in Complex Scenescited by 12
  4. 2021ADC: Adversarial attacks against object Detection that evade Context consistency checkscited by 12
  5. 2023Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Modelscited by 12
  6. 2024Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusioncited by 11
  7. 2022TPC: Transformation-Specific Smoothing for Point Cloud Modelscited by 10
  8. 2022CARE: Certifiably Robust Learning with Reasoning via Variational Inferencecited by 10
  9. 2023TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentationcited by 10
  10. 2023Uncertainty-weighted Loss Functions for Improved Adversarial Attacks on Semantic Segmentationcited by 9
  11. 2022Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularizationcited by 8
  12. 2021Semantically Stealthy Adversarial Attacks against Segmentation Modelscited by 7
  13. 2021We Can Always Catch You: Detecting Adversarial Patched Objects WITH or WITHOUT Signaturecited by 6
  14. 2023Influencer Backdoor Attack on Semantic Segmentationcited by 5
  15. 2023A Certified Radius-Guided Attack Framework to Image Segmentation Modelscited by 5
  16. 2023Uncertainty-based Detection of Adversarial Attacks in Semantic Segmentationcited by 5
  17. 2023A Review of Adversarial Attacks in Computer Visioncited by 5
  18. 2021Auditing AI models for Verified Deployment under Semantic Specificationscited by 4
  19. 2021Multilingual and Multilabel Emotion Recognition using Virtual Adversarial Trainingcited by 4
  20. 2023Transferable Attack for Semantic Segmentationcited by 4
  21. 2022Sensor Data Validation and Driving Safety in Autonomous Driving Systemscited by 3
  22. 2023PEARL: Preprocessing Enhanced Adversarial Robust Learning of Image Deraining for Semantic Segmentationcited by 3
  23. 2024Attack Deterministic Conditional Image Generative Models for Diverse and Controllable Generationcited by 2
  24. 2023Boosting Verified Training for Robust Image Classifications via Abstractioncited by 1
  25. 2024Detecting Adversarial Attacks in Semantic Segmentation via Uncertainty Estimation: A Deep Analysiscited by 1
  26. 2021DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flowscited by 0
  27. 2021Adversarial Attacks with Time-Scale Representationscited by 0
  28. 2025RanAT4BIE: Random Adversarial Training for Biomedical Information Extractioncited by 0