TransCAB: Transferable Clean-Annotation Backdoor to Object Detection with Natural Trigger in Real-World

• URL: http://arxiv.org/abs/2209.02339v2
• Date: Sat, 2 Sep 2023 08:23:33 GMT
• Title: TransCAB: Transferable Clean-Annotation Backdoor to Object Detection with Natural Trigger in Real-World
• Authors: Hua Ma, Yinshan Li, Yansong Gao, Zhi Zhang, Alsharif Abuadbba, Anmin Fu, Said F. Al-Sarawi, Nepal Surya, Derek Abbott
• Abstract summary: We propose MACAB that crafts clean-annotated images to stealthily implant the backdoor into the object detectors trained on them. We observe that the backdoor effect of both misclassification and the cloaking are robustly achieved in the wild. MACAB exhibits more than 90% attack success rate under various real-world scenes.
• Score: 16.14185033829483
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Object detection is the foundation of various critical computer-vision tasks such as segmentation, object tracking, and event detection. To train an object detector with satisfactory accuracy, a large amount of data is required. However, due to the intensive workforce involved with annotating large datasets, such a data curation task is often outsourced to a third party or relied on volunteers. This work reveals severe vulnerabilities of such data curation pipeline. We propose MACAB that crafts clean-annotated images to stealthily implant the backdoor into the object detectors trained on them even when the data curator can manually audit the images. We observe that the backdoor effect of both misclassification and the cloaking are robustly achieved in the wild when the backdoor is activated with inconspicuously natural physical triggers. Backdooring non-classification object detection with clean-annotation is challenging compared to backdooring existing image classification tasks with clean-label, owing to the complexity of having multiple objects within each frame, including victim and non-victim objects. The efficacy of the MACAB is ensured by constructively i abusing the image-scaling function used by the deep learning framework, ii incorporating the proposed adversarial clean image replica technique, and iii combining poison data selection criteria given constrained attacking budget. Extensive experiments demonstrate that MACAB exhibits more than 90% attack success rate under various real-world scenes. This includes both cloaking and misclassification backdoor effect even restricted with a small attack budget. The poisoned samples cannot be effectively identified by state-of-the-art detection techniques.The comprehensive video demo is at https://youtu.be/MA7L_LpXkp4, which is based on a poison rate of 0.14% for YOLOv4 cloaking backdoor and Faster R-CNN misclassification backdoor.

Related papers

• Comprehensive Evaluation of Cloaking Backdoor Attacks on Object Detector in Real-World [31.24615007171502]
  This dataset is tailored for the study of physical backdoors in object detectors. We extensively evaluate four popular object detection algorithms using 19 videos (totaling approximately 11,800 frames) in real-world scenarios. Our results demonstrate that the backdoor attack exhibits remarkable robustness against various factors, including movement, distance, angle, non-rigid deformation, and lighting.
  arXiv  Detail & Related papers  (2025-01-25T06:43:20Z)
• Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images [0.0]
  Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. We introduce a groundbreaking method to detect unseen backdoored images during both training and inference. Our approach trains learnable text prompts to differentiate clean images from those with hidden backdoor triggers.
  arXiv  Detail & Related papers  (2024-12-11T19:54:14Z)
• Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving [17.637155085620634]
  Detector Collapse (DC) is a brand-new backdoor attack paradigm tailored for object detection. DC is designed to instantly incapacitate detectors (i.e., severely impairing detector's performance and culminating in a denial-of-service) We introduce a novel poisoning strategy exploiting natural objects, enabling DC to act as a practical backdoor in real-world environments.
  arXiv  Detail & Related papers  (2024-04-17T13:12:14Z)
• Attacking by Aligning: Clean-Label Backdoor Attacks on Object Detection [24.271795745084123]
  Deep neural networks (DNNs) have shown unprecedented success in object detection tasks. Backdoor attacks on object detection tasks have not been properly investigated and explored. We propose a simple yet effective backdoor attack method against object detection without modifying the ground truth annotations.
  arXiv  Detail & Related papers  (2023-07-19T22:46:35Z)
• Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder [57.739693628523]
  We propose a framework for blind backdoor defense with Masked AutoEncoder (BDMAE) BDMAE detects possible triggers in the token space using image structural similarity and label consistency between the test image and MAE restorations. Our approach is blind to the model restorations, trigger patterns and image benignity.
  arXiv  Detail & Related papers  (2023-03-27T19:23:33Z)
• Untargeted Backdoor Attack against Object Detection [69.63097724439886]
  We design a poison-only backdoor attack in an untargeted manner, based on task characteristics. We show that, once the backdoor is embedded into the target model by our attack, it can trick the model to lose detection of any object stamped with our trigger patterns.
  arXiv  Detail & Related papers  (2022-11-02T17:05:45Z)
• Training set cleansing of backdoor poisoning by self-supervised representation learning [0.0]
  A backdoor or Trojan attack is an important type of data poisoning attack against deep neural network (DNN) We show that supervised training may build stronger association between the backdoor pattern and the associated target class than that between normal features and the true class of origin. We propose to use unsupervised representation learning to avoid emphasising backdoor-poisoned training samples and learn a similar feature embedding for samples of the same class.
  arXiv  Detail & Related papers  (2022-10-19T03:29:58Z)
• Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation [48.238349062995916]
  We find that highly effective backdoors can be easily inserted using rotation-based image transformation. Our work highlights a new, simple, physically realizable, and highly effective vector for backdoor attacks.
  arXiv  Detail & Related papers  (2022-07-22T00:21:18Z)
• Adversarially-Aware Robust Object Detector [85.10894272034135]
  We propose a Robust Detector (RobustDet) based on adversarially-aware convolution to disentangle gradients for model learning on clean and adversarial images. Our model effectively disentangles gradients and significantly enhances the detection robustness with maintaining the detection ability on clean images.
  arXiv  Detail & Related papers  (2022-07-13T13:59:59Z)
• BadDet: Backdoor Attacks on Object Detection [42.40418007499009]
  We propose four kinds of backdoor attacks for object detection task. A trigger can falsely generate an object of the target class. A single trigger can change the predictions of all objects in an image to the target class.
  arXiv  Detail & Related papers  (2022-05-28T18:02:11Z)
• ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking [95.6347501381882]
  Object detectors are found to be vulnerable to physical-world patch hiding attacks. We propose ObjectSeeker as a framework for building certifiably robust object detectors.
  arXiv  Detail & Related papers  (2022-02-03T19:34:25Z)
• Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning [54.15013757920703]
  We propose the confusing perturbations-induced backdoor attack (CIBA) It injects a small number of poisoned images with the correct label into the training data. We have conducted extensive experiments to verify the effectiveness of our proposed CIBA.
  arXiv  Detail & Related papers  (2021-09-18T07:56:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.