Butterfly Effect Attack: Tiny and Seemingly Unrelated Perturbations for Object Detection

• URL: http://arxiv.org/abs/2211.07483v1
• Date: Mon, 14 Nov 2022 16:07:14 GMT
• Title: Butterfly Effect Attack: Tiny and Seemingly Unrelated Perturbations for Object Detection
• Authors: Nguyen Anh Vu Doan, Arda Y\"uksel, Chih-Hong Cheng
• Abstract summary: This work aims to explore and identify tiny and seemingly unrelated perturbations of images in object detection. We characterize the degree of "unrelatedness" of an object by the pixel distance between the occurred perturbation and the object. The result successfully demonstrates that (invisible) perturbations on the right part of the image can drastically change the outcome of object detection on the left.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This work aims to explore and identify tiny and seemingly unrelated perturbations of images in object detection that will lead to performance degradation. While tininess can naturally be defined using $L_p$ norms, we characterize the degree of "unrelatedness" of an object by the pixel distance between the occurred perturbation and the object. Triggering errors in prediction while satisfying two objectives can be formulated as a multi-objective optimization problem where we utilize genetic algorithms to guide the search. The result successfully demonstrates that (invisible) perturbations on the right part of the image can drastically change the outcome of object detection on the left. An extensive evaluation reaffirms our conjecture that transformer-based object detection networks are more susceptible to butterfly effects in comparison to single-stage object detection networks such as YOLOv5.

Related papers

• Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training [84.95281245784348]
  Overemphasizing co-occurrence relationships can cause the overfitting issue of the model. We provide a causal inference framework to show that the correlative features caused by the target object and its co-occurring objects can be regarded as a mediator.
  arXiv  Detail & Related papers  (2024-04-09T13:13:24Z)
• Spatial Coherence Loss: All Objects Matter in Salient and Camouflaged Object Detection [3.03995893427722]
  We show that for accurate semantic analysis, the network needs to learn all object-level predictions that appear at any stage of learning. We propose a novel loss function, Spatial Coherence Loss (SCLoss), that incorporates the mutual response between adjacent pixels into the widely-used single-response loss functions.
  arXiv  Detail & Related papers  (2024-02-28T20:27:49Z)
• Differential Evolution based Dual Adversarial Camouflage: Fooling Human Eyes and Object Detectors [0.190365714903665]
  We propose a dual adversarial camouflage (DE_DAC) method, composed of two stages to fool human eyes and object detectors simultaneously. In the first stage, we optimize the global texture to minimize the discrepancy between the rendered object and the scene images. In the second stage, we design three loss functions to optimize the local texture, making object detectors ineffective.
  arXiv  Detail & Related papers  (2022-10-17T09:07:52Z)
• Object Detection in Aerial Images with Uncertainty-Aware Graph Network [61.02591506040606]
  We propose a novel uncertainty-aware object detection framework with a structured-graph, where nodes and edges are denoted by objects. We refer to our model as Uncertainty-Aware Graph network for object DETection (UAGDet)
  arXiv  Detail & Related papers  (2022-08-23T07:29:03Z)
• High-resolution Iterative Feedback Network for Camouflaged Object Detection [128.893782016078]
  Spotting camouflaged objects that are visually assimilated into the background is tricky for object detection algorithms. We aim to extract the high-resolution texture details to avoid the detail degradation that causes blurred vision in edges and boundaries. We introduce a novel HitNet to refine the low-resolution representations by high-resolution features in an iterative feedback manner.
  arXiv  Detail & Related papers  (2022-03-22T11:20:21Z)
• Decoupled Adaptation for Cross-Domain Object Detection [69.5852335091519]
  Cross-domain object detection is more challenging than object classification. D-adapt achieves a state-of-the-art results on four cross-domain object detection tasks.
  arXiv  Detail & Related papers  (2021-10-06T08:43:59Z)
• Slender Object Detection: Diagnoses and Improvements [74.40792217534]
  In this paper, we are concerned with the detection of a particular type of objects with extreme aspect ratios, namely textbfslender objects. For a classical object detection method, a drastic drop of $18.9%$ mAP on COCO is observed, if solely evaluated on slender objects.
  arXiv  Detail & Related papers  (2020-11-17T09:39:42Z)
• Adaptive Object Detection with Dual Multi-Label Prediction [78.69064917947624]
  We propose a novel end-to-end unsupervised deep domain adaptation model for adaptive object detection. The model exploits multi-label prediction to reveal the object category information in each image. We introduce a prediction consistency regularization mechanism to assist object detection.
  arXiv  Detail & Related papers  (2020-03-29T04:23:22Z)

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.