Transferable Adversarial Attacks for Image and Video Object Detection

Abstract

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.

arXiv commentIJCAI2019 oral

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Certified Defenses against Adversarial Examples
• Robust Physical-World Attacks on Deep Learning Models
• Generating Adversarial Examples with Adversarial Networks
• Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
• Flow-Guided Feature Aggregation for Video Object Detection
• Adversarial Examples for Semantic Segmentation and Object Detection
• Towards Interpretable Deep Neural Networks by Leveraging Adversarial Examples
• Robust Adversarial Perturbation on Deep Proposal-based Models
• Sparse Adversarial Perturbations for Videos
• Optimizing Video Object Detection via a Scale-Time Lattice

Cited by in corpus (11)

• Secure and Trustworthy Artificial Intelligence-Extended Reality (AI-XR) for Metaverses
• DPAttack: Diffused Patch Attacks against Universal Object Detection
• Transferable Universal Adversarial Perturbations Using Generative Models
• Adversarial Examples on Object Recognition: A Comprehensive Survey
• Category-wise Attack: Transferable Adversarial Examples for Anchor Free Object Detection
• The Intriguing Relation Between Counterfactual Explanations and Adversarial Examples
• Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible Noises
• Efficient Adversarial Attacks for Visual Object Tracking
• Membership Inference Attacks Against Object Detection Models
• Towards Adversarially Robust Object Detection
• Understanding Object Detection Through An Adversarial Lens