# Distributed Black-box Attack: Do Not Overestimate Black-box Attacks

Source: [Distributed Black-box Attack: Do Not Overestimate Black-box Attacks](<https://www.sota2.com/research/paper/68fa777a1e209131cea73704>)

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

Data updated: 2025-10-26T04:19:49.174Z

Authors: Han Wu, Sareh Rowlands, Johan Wahlstrom

Published: 2022-10-28T19:14:03.000Z

## Abstract

As cloud computing becomes pervasive, deep learning models are deployed on cloud servers and then provided as APIs to end users. However, black-box adversarial attacks can fool image classification models without access to model structure and weights. Recent studies have reported attack success rates of over 95% with fewer than 1,000 queries. Then the question arises: whether black-box attacks have become a real threat against cloud APIs? To shed some light on this, our research indicates that black-box attacks are not as effective against cloud APIs as proposed in research papers due to several common mistakes that overestimate the efficiency of black-box attacks. To avoid similar mistakes, we conduct black-box attacks directly on cloud APIs rather than local models.

## 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/2210.16371>)

[PDF](<https://arxiv.org/pdf/2210.16371.pdf>)