Context-Aware Transfer Attacks for Object Detection

TL;DR

This paper introduces a novel context-aware attack method for object detectors that leverages object co-occurrence and spatial relationships to improve transfer success rates in blackbox settings, outperforming existing methods.

Contribution

The paper presents a new approach using object co-occurrence and spatial context to generate more effective transfer attacks on object detectors, a less explored area.

Findings

Achieves up to 20% higher transfer success rates than state-of-the-art methods.

Effective on multiple object detectors with PASCAL VOC and MS COCO datasets.

Demonstrates the importance of context information in adversarial attacks.

Abstract

Blackbox transfer attacks for image classifiers have been extensively studied in recent years. In contrast, little progress has been made on transfer attacks for object detectors. Object detectors take a holistic view of the image and the detection of one object (or lack thereof) often depends on other objects in the scene. This makes such detectors inherently context-aware and adversarial attacks in this space are more challenging than those targeting image classifiers. In this paper, we present a new approach to generate context-aware attacks for object detectors. We show that by using co-occurrence of objects and their relative locations and sizes as context information, we can successfully generate targeted mis-categorization attacks that achieve higher transfer success rates on blackbox object detectors than the state-of-the-art. We test our approach on a variety of object detectors with images from PASCAL VOC and MS COCO datasets and demonstrate up to $20$ percentage points improvement in performance compared to the other state-of-the-art methods.