Transferable Adversarial Attacks for Image and Video Object Detection
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.
Code (3)
Tasks
Generative Adversarial NetworkObjectobject-detectionObject DetectionVideo Object DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Adversarial Pixel Restoration as a Pretext Task for Transferable Perturbations
Transferable adversarial attacks optimize adversaries from a pretrained surrogate model and known label space to fool the unknown black-box models. Therefore, these attacks are restricted by the availability of an effect…
object-detectionObject DetectionVideo SegmentationVideo Semantic SegmentationCross-Modal Transferable Adversarial Attacks from Images to Videos
Recent studies have shown that adversarial examples hand-crafted on one white-box model can be used to attack other black-box models. Such cross-model transferability makes it feasible to perform black-box attacks, which…
Video RecognitionFeature Importance-aware Transferable Adversarial Attacks
Transferability of adversarial examples is of central importance for attacking an unknown model, which facilitates adversarial attacks in more practical scenarios, e.g., black-box attacks. Existing transferable attacks t…
Feature ImportanceTemporally-Transferable Perturbations: Efficient, One-Shot Adversarial Attacks for Online Visual Object Trackers
In recent years, the trackers based on Siamese networks have emerged as highly effective and efficient for visual object tracking (VOT). While these methods were shown to be vulnerable to adversarial attacks, as most dee…
Object TrackingVisual Object TrackingTRAIL: Transferable Robust Adversarial Images via Latent diffusion
Adversarial attacks exploiting unrestricted natural perturbations present severe security risks to deep learning systems, yet their transferability across models remains limited due to distribution mismatches between gen…
DenoisingTest-time Adaptation