mlsanityData to 7 Oct 2026

Transferable Adversarial Attacks for Image and Video Object Detection

arXiv 1811.12641 ↗First posted 30 Nov 2018cs.CVcited by 109

Not on the map. Why?

Abstract (arXiv)

Adversarial examples have been demonstrated to threaten many computer vision tasks including object detection. However, the existing attacking methods for object detection have two limitations: poor transferability, which denotes that the generated adversarial examples have low success rate to attack other kinds of detection methods, and high computation cost, which means that they need more time to generate an adversarial image, and therefore are difficult to deal with the video data. To address these issues, we utilize a generative mechanism to obtain the adversarial image and video. In this way, the processing time is reduced. To enhance the transferability, we destroy the feature maps extracted from the feature network, which usually constitutes the basis of object detectors. The proposed method is based on the Generative Adversarial Network (GAN) framework, where we combine the high-level class loss and low-level feature loss to jointly train the adversarial example generator. A series of experiments conducted on PASCAL VOC and ImageNet VID datasets show that our method can efficiently generate image and video adversarial examples, and more importantly, these adversarial examples have better transferability, and thus, are able to simultaneously attack two kinds of representative object detection models: proposal based models like Faster-RCNN, and regression based models like SSD.

Key facts. Cited by 109 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 20; 2023: 21; 2024: 24; 2025: 19; 2026: 11.

109 papers.

Sort:

By area:

  1. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
  2. 2024Jailbreak Vision Language Models via Bi-Modal Adversarial Promptcited by 103
  3. 2022LAS-AT: Adversarial Training with Learnable Attack Strategycited by 94
  4. 2024VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Modelscited by 83
  5. 2022Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detectioncited by 79
  6. 2023BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIPcited by 63
  7. 2023Structure Invariant Transformation for better Adversarial Transferabilitycited by 61
  8. 2022T-SEA: Transfer-based Self-Ensemble Attack on Object Detectioncited by 59
  9. 2022A Large-scale Multiple-objective Method for Black-box Attack against Object Detectioncited by 55
  10. 2021Triangle Attack: A Query-efficient Decision-based Adversarial Attackcited by 48
  11. 2023Boosting Adversarial Transferability by Achieving Flat Local Maximacited by 48
  12. 2024Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMscited by 48
38 more
  1. 2021Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Drivingcited by 45
  2. 2023A Survey on Transferability of Adversarial Examples across Deep Neural Networkscited by 43
  3. 2025Manipulating Multimodal Agents via Cross-Modal Prompt Injectioncited by 42
  4. 2021Boosting Fast Adversarial Training with Learnable Adversarial Initializationcited by 40
  5. 2023Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Featurescited by 35
  6. 2024Visual Adversarial Attack on Vision-Language Models for Autonomous Drivingcited by 35
  7. 2022Prior-Guided Adversarial Initialization for Fast Adversarial Trainingcited by 34
  8. 2023Diversifying the High-level Features for better Adversarial Transferabilitycited by 34
  9. 2024Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detectioncited by 34
  10. 2024Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearningcited by 31
  11. 2022Towards Efficient Adversarial Training on Vision Transformerscited by 29
  12. 2024Effectiveness Assessment of Recent Large Vision-Language Modelscited by 29
  13. 2024Compromising Embodied Agents with Contextual Backdoor Attackscited by 29
  14. 2021DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attackscited by 28
  15. 2021Class-Aware Robust Adversarial Training for Object Detectioncited by 27
  16. 2023Rethinking the Backward Propagation for Adversarial Transferabilitycited by 27
  17. 2025Agentic AI Security: Threats, Defenses, Evaluation, and Open Challengescited by 26
  18. 2024Towards Robust Physical-world Backdoor Attacks on Lane Detectioncited by 25
  19. 2021Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuningcited by 24
  20. 2024Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Cloudscited by 24
  21. 2024Learning to Transform Dynamically for Better Adversarial Transferabilitycited by 23
  22. 2025Black-Box Adversarial Attack on Vision Language Models for Autonomous Drivingcited by 23
  23. 2022Hardly Perceptible Trojan Attack against Neural Networks with Bit Flipscited by 21
  24. 2022Adversarially-Aware Robust Object Detectorcited by 20
  25. 2024Interpreting Object-level Foundation Models via Visual Precision Searchcited by 20
  26. 2022Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentationcited by 19
  27. 2021Inconspicuous Adversarial Patches for Fooling Image Recognition Systems on Mobile Devicescited by 18
  28. 2021Context-Aware Transfer Attacks for Object Detectioncited by 18
  29. 2024LanEvil: Benchmarking the Robustness of Lane Detection to Environmental Illusionscited by 18
  30. 2025T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attackscited by 18
  31. 2022How Do We Fail? Stress Testing Perception in Autonomous Vehiclescited by 17
  32. 2022Zero-Query Transfer Attacks on Context-Aware Object Detectorscited by 17
  33. 2025T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Modelscited by 17
  34. 2023Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challengescited by 16
  35. 2023Ensemble-based Blackbox Attacks on Dense Predictioncited by 16
  36. 2024Object Detectors in the Open Environment: Challenges, Solutions, and Outlookcited by 13
  37. 2025E2AT: Multimodal Jailbreak Defense via Dynamic Joint Optimization for Multimodal Large Language Modelscited by 12
  38. 2021Adversarial Feature Augmentation and Normalization for Visual Recognitioncited by 11

50 most cited of 109 All 109 (JSON)