mlsanityData to 7 Oct 2026

Exploiting Multi-Object Relationships for Detecting Adversarial Attacks in Complex Scenes

arXiv 2108.08421 ↗First posted 19 Aug 2021cs.CV cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

Vision systems that deploy Deep Neural Networks (DNNs) are known to be vulnerable to adversarial examples. Recent research has shown that checking the intrinsic consistencies in the input data is a promising way to detect adversarial attacks (e.g., by checking the object co-occurrence relationships in complex scenes). However, existing approaches are tied to specific models and do not offer generalizability. Motivated by the observation that language descriptions of natural scene images have already captured the object co-occurrence relationships that can be learned by a language model, we develop a novel approach to perform context consistency checks using such language models. The distinguishing aspect of our approach is that it is independent of the deployed object detector and yet offers very high accuracy in terms of detecting adversarial examples in practical scenes with multiple objects.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 33 of its 47 references that are in the map. First posted on arXiv 19 Aug 2021.

Builds on

33 of 47 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  8. 2013Intriguing properties of neural networkscited by 5,114
  9. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  10. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  11. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  12. 2016Adversarial examples in the physical worldcited by 1,762
21 more
  1. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  2. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  3. 2017Scene Graph Generation by Iterative Message Passingcited by 462
  4. 2016Visual Relationship Detection with Language Priorscited by 333
  5. 2018Image Generation from Scene Graphscited by 324
  6. 2017Relation Networks for Object Detectioncited by 305
  7. 2017Detecting Adversarial Samples from Artifactscited by 244
  8. 2018Exploring Visual Relationship for Image Captioningcited by 215
  9. 2018Physical Adversarial Examples for Object Detectorscited by 163
  10. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
  11. 2019Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Drivingcited by 151
  12. 2018Modeling Visual Context is Key to Augmenting Object Detection Datasetscited by 106
  13. 2017Detecting Adversarial Image Examples in Deep Networks with Adaptive Noise Reductioncited by 49
  14. 2018Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationshipscited by 41
  15. 2018Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentationcited by 40
  16. 2016Early Methods for Detecting Adversarial Imagescited by 36
  17. 2018Detection based Defense against Adversarial Examples from the Steganalysis Point of Viewcited by 32
  18. 2020Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistencycited by 16
  19. 2017Exploring the Bounds of the Utility of Context for Object Detectioncited by 10
  20. 2019Detecting Adversarial Attacks On Audiovisual Speech Recognitioncited by 8
  21. 2019Identifying and Resisting Adversarial Videos Using Temporal Consistencycited by 7

Built on by

Cited by year (2026 to 7 Oct)

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

12 papers.

  1. 2021Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformationscited by 28
  2. 2021Context-Aware Transfer Attacks for Object Detectioncited by 18
  3. 2022Zero-Query Transfer Attacks on Context-Aware Object Detectorscited by 17
  4. 2022GAMA: Generative Adversarial Multi-Object Scene Attackscited by 13
  5. 2021Multi-Expert Adversarial Attack Detection in Person Re-identification Using Context Inconsistencycited by 12
  6. 2021ADC: Adversarial attacks against object Detection that evade Context consistency checkscited by 12
  7. 2024Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learningcited by 4
  8. 2025Factor Graph-based Interpretable Neural Networkscited by 2
  9. 2023GLOW: Global Layout Aware Attacks on Object Detectioncited by 1
  10. 2024On Feasibility of Intent Obfuscating Attackscited by 0
  11. 2026Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentationcited by 0
  12. 2026AEGIS: A Semantic GAN and Evidential Learning Frameworkfor Robust Adversarial Detection in Vision Sensorscited by 0