# Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors

Source: [Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors](<https://www.sota2.com/research/paper/68fa572f1e209131ce9a326c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T05:14:50.626Z

Authors: Zuxuan Wu, Ser-Nam Lim, Larry Davis, Tom Goldstein

Published: 2019-10-31T17:56:29.000Z

## Abstract

We present a systematic study of adversarial attacks on state-of-the-art object detection frameworks. Using standard detection datasets, we train patterns that suppress the objectness scores produced by a range of commonly used detectors, and ensembles of detectors. Through extensive experiments, we benchmark the effectiveness of adversarially trained patches under both white-box and black-box settings, and quantify transferability of attacks between datasets, object classes, and detector models. Finally, we present a detailed study of physical world attacks using printed posters and wearable clothes, and rigorously quantify the performance of such attacks with different metrics.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1910.14667>)

[PDF](<https://arxiv.org/pdf/1910.14667.pdf>)
