Butterfly Effect Attack: Tiny and Seemingly Unrelated Perturbations for Object Detection

TL;DR

This paper investigates how tiny, seemingly unrelated image perturbations can drastically impair object detection, revealing vulnerabilities especially in transformer-based models through a multi-objective genetic algorithm approach.

Contribution

It introduces a novel method to identify minimal, unrelated perturbations that significantly degrade object detection performance, highlighting model vulnerabilities.

Findings

Perturbations on one part of an image can affect detection on another.

Transformer-based detectors are more vulnerable than YOLOv5.

Genetic algorithms effectively find impactful perturbations.

Abstract

This work aims to explore and identify tiny and seemingly unrelated perturbations of images in object detection that will lead to performance degradation. While tininess can naturally be defined using $L_p$ norms, we characterize the degree of "unrelatedness" of an object by the pixel distance between the occurred perturbation and the object. Triggering errors in prediction while satisfying two objectives can be formulated as a multi-objective optimization problem where we utilize genetic algorithms to guide the search. The result successfully demonstrates that (invisible) perturbations on the right part of the image can drastically change the outcome of object detection on the left. An extensive evaluation reaffirms our conjecture that transformer-based object detection networks are more susceptible to butterfly effects in comparison to single-stage object detection networks such as YOLOv5.