mlsanityData to 14 Oct 2026

Adversarial Examples for Semantic Segmentation and Object Detection

arXiv 1703.08603 ↗First posted 24 Mar 2017cs.CVcited by 275

Not on the map. Why?

Abstract (arXiv)

It has been well demonstrated that adversarial examples, i.e., natural images with visually imperceptible perturbations added, generally exist for deep networks to fail on image classification. In this paper, we extend adversarial examples to semantic segmentation and object detection which are much more difficult. Our observation is that both segmentation and detection are based on classifying multiple targets on an image (e.g., the basic target is a pixel or a receptive field in segmentation, and an object proposal in detection), which inspires us to optimize a loss function over a set of pixels/proposals for generating adversarial perturbations. Based on this idea, we propose a novel algorithm named Dense Adversary Generation (DAG), which generates a large family of adversarial examples, and applies to a wide range of state-of-the-art deep networks for segmentation and detection. We also find that the adversarial perturbations can be transferred across networks with different training data, based on different architectures, and even for different recognition tasks. In particular, the transferability across networks with the same architecture is more significant than in other cases. Besides, summing up heterogeneous perturbations often leads to better transfer performance, which provides an effective method of black-box adversarial attack.

Key facts. Cited by 275 papers in the map (data through 14 Oct 2026). First posted on arXiv 24 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 65; 2022: 57; 2023: 64; 2024: 39; 2025: 32; 2026: 18.

275 papers.

Sort:

By area:

  1. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 280
  2. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
  3. 2023DDP: Diffusion Model for Dense Visual Predictioncited by 148
  4. 2021Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentationcited by 134
  5. 2022Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detectioncited by 79
  6. 2022SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustnesscited by 74
  7. 2021HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noisecited by 65
  8. 2022T-SEA: Transfer-based Self-Ensemble Attack on Object Detectioncited by 59
  9. 2021Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attackscited by 55
  10. 2022A Large-scale Multiple-objective Method for Black-box Attack against Object Detectioncited by 55
  11. 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 52
  12. 2021Adversarial Attacks On Multi-Agent Communicationcited by 49
38 more
  1. 2022AdvDO: Realistic Adversarial Attacks for Trajectory Predictioncited by 49
  2. 2022Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyondcited by 48
  3. 2021Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Drivingcited by 45
  4. 2022Exploring Frequency Adversarial Attacks for Face Forgery Detectioncited by 45
  5. 2021Robust and Accurate Object Detection via Adversarial Learningcited by 42
  6. 2023RoboBEV: Towards Robust Bird's Eye View Perception under Corruptionscited by 42
  7. 2024Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Drivingcited by 41
  8. 2021LiBRe: A Practical Bayesian Approach to Adversarial Detectioncited by 40
  9. 2021Improved Text Classification via Contrastive Adversarial Trainingcited by 38
  10. 2023Understanding the Robustness of 3D Object Detection with Bird's-Eye-View Representations in Autonomous Drivingcited by 37
  11. 2021Scalable Certified Segmentation via Randomized Smoothingcited by 35
  12. 20213DB: A Framework for Debugging Computer Vision Modelscited by 31
  13. 2022On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Drivingcited by 30
  14. 2022Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loopcited by 30
  15. 2021DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attackscited by 29
  16. 2021Corner Case Generation and Analysis for Safety Assessment of Autonomous Vehiclescited by 27
  17. 2021Class-Aware Robust Adversarial Training for Object Detectioncited by 27
  18. 2023Semantic Image Segmentation: Two Decades of Researchcited by 27
  19. 2021TAFIM: Targeted Adversarial Attacks against Facial Image Manipulationscited by 26
  20. 2021Fooling LiDAR Perception via Adversarial Trajectory Perturbationcited by 25
  21. 2025MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attackscited by 24
  22. 2022Proximal Splitting Adversarial Attacks for Semantic Segmentationcited by 23
  23. 2024Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Modelscited by 23
  24. 2024Adversarial Attacks of Vision Tasks in the Past 10 Years: A Surveycited by 23
  25. 2022Dangerous Cloaking: Natural Trigger based Backdoor Attacks on Object Detectors in the Physical Worldcited by 22
  26. 2022SoK: On the Semantic AI Security in Autonomous Drivingcited by 22
  27. 2023TPatch: A Triggered Physical Adversarial Patchcited by 22
  28. 2022Benchmarking Adversarial Patch Against Aerial Detectioncited by 21
  29. 2021Enhancing MR Image Segmentation with Realistic Adversarial Data Augmentationcited by 20
  30. 2022Adversarial Attack and Defense of YOLO Detectors in Autonomous Driving Scenarioscited by 20
  31. 2022Adversarially-Aware Robust Object Detectorcited by 20
  32. 2023Backdoor Attack with Sparse and Invisible Triggercited by 20
  33. 2023A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attackscited by 19
  34. 2021RPATTACK: Refined Patch Attack on General Object Detectorscited by 18
  35. 2021Context-Aware Transfer Attacks for Object Detectioncited by 18
  36. 2022How Do We Fail? Stress Testing Perception in Autonomous Vehiclescited by 18
  37. 2022Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networkscited by 18
  38. 2021MagDR: Mask-guided Detection and Reconstruction for Defending Deepfakescited by 17

50 most cited of 275 All 275 (JSON)