Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection

Dongsu Song, Daehwa Ko, Jay Hoon Jung

Keywords: Adversarial attack, Query-based pixel attack, Image classification, Object detection, RL

Abstract:

It is well known that query-based attacks tend to have relatively higher success
rates in adversarial black-box attacks. While research on black-box attacks is actively
being conducted, relatively few studies have focused on pixel attacks that
target only a limited number of pixels. In image classification, query-based pixel
attacks often rely on patches, which heavily depend on randomness and neglect
the fact that scattered pixels are more suitable for adversarial attacks. Moreover, to
the best of our knowledge, query-based pixel attacks have not been explored in the
field of object detection. To address these issues, we propose a novel pixel-based
black-box attack called Remember and Forget Pixel Attack using Reinforcement
Learning(RFPAR), consisting of two main components: the Remember and Forget
processes. RFPAR mitigates randomness and avoids patch dependency by
leveraging rewards generated through a one-step RL algorithm to perturb pixels.
RFPAR effectively creates perturbed images that minimize the confidence scores
while adhering to limited pixel constraints. Furthermore, we advance our proposed
attack beyond image classification to object detection, where RFPAR reduces
the confidence scores of detected objects to avoid detection. Experiments
on the ImageNet-1K dataset for classification show that RFPAR outperformed
state-of-the-art query-based pixel attacks. For object detection, using the MSCOCO
dataset with YOLOv8 and DDQ, RFPAR demonstrates comparable mAP
reduction to state-of-the-art query-based attack while requiring fewer query. Further
experiments on the Argoverse dataset using YOLOv8 confirm that RFPAR
effectively removed objects on a larger scale dataset. Our code is available at
https://github.com/KAU-QuantumAILab/RFPAR.

Primary Area: Machine vision

Flagged For Ethics Review: true

Submission Number: 14897