Copy and Paste: A Simple But Effective Initialization Method for Black-Box Adversarial Attacks
Many optimization methods for generating black-box adversarial examples have been proposed, but the aspect of initializing said optimizers has not been considered in much detail. We show that the choice of starting points is indeed crucial, and that the performance of state-of-the-art attacks depends on it. First, we discuss desirable properties of starting points for attacking image classifiers, and how they can be chosen to increase query efficiency. Notably, we find that simply copying small patches from other images is a valid strategy. We then present an evaluation on ImageNet that clearly demonstrates the effectiveness of this method: Our initialization scheme reduces the number of queries required for a state-of-the-art Boundary Attack by 81%, significantly outperforming previous results reported for targeted black-box adversarial examples.
Code (1)
Tasks
validSimilar Papers 제목 키워드 기반
Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation
Building instance segmentation models that are data-efficient and can handle rare object categories is an important challenge in computer vision. Leveraging data augmentations is a promising direction towards addressing …
Data AugmentationImage AugmentationInstance SegmentationObject Detection+2X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion
Copy-Paste is a simple and effective data augmentation strategy for instance segmentation. By randomly pasting object instances onto new background images, it creates new training data for free and significantly boosts t…
Data AugmentationInstance SegmentationObjectObject Detection+4Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance Segmentation
Modern object detection and instance segmentation networks stumble when picking out humans in crowded or highly occluded scenes. Yet, these are often scenarios where we require our detectors to work well. Many works have…
Human Instance SegmentationInstance Segmentationobject-detectionObject Detection+2Copy-Paste to Mitigate Large Language Model Hallucinations
While Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to generate contextually grounded responses, contextual faithfulness remains challenging as LLMs may not consistently trust provided context…
Enrich the content of the image Using Context-Aware Copy Paste
Data augmentation remains a widely utilized technique in deep learning, particularly in tasks such as image classification, semantic segmentation, and object detection. Among them, Copy-Paste is a simple yet effective me…
Data AugmentationDiversityimage-classificationImage Classification+3