# There are No Bit Parts for Sign Bits in Black-Box Attacks

Source: [There are No Bit Parts for Sign Bits in Black-Box Attacks](<https://www.sota2.com/research/paper/68fa658f1e209131cea0b2e3>)

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

Data updated: 2025-10-25T21:30:43.473Z

Authors: Abdullah Al-Dujaili, Una-May O'Reilly

Published: 2019-02-19T05:01:23.000Z

## Abstract

We present a black-box adversarial attack algorithm which sets new state-of-the-art model evasion rates for query efficiency in the $\\ell\_\\infty$ and $\\ell\_2$ metrics, where only loss-oracle access to the model is available. On two public black-box attack challenges, the algorithm achieves the highest evasion rate, surpassing all of the submitted attacks. Similar performance is observed on a model that is secure against substitute-model attacks. For standard models trained on the MNIST, CIFAR10, and IMAGENET datasets, averaged over the datasets and metrics, the algorithm is 3.8x less failure-prone, and spends in total 2.5x fewer queries than the current state-of-the-art attacks combined given a budget of 10, 000 queries per attack attempt. Notably, it requires no hyperparameter tuning or any data/time-dependent prior. The algorithm exploits a new approach, namely sign-based rather than magnitude-based gradient estimation. This shifts the estimation from continuous to binary black-box optimization. With three properties of the directional derivative, we examine three approaches to adversarial attacks. This yields a superior algorithm breaking a standard MNIST model using just 12 queries on average!

## 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/1902.06894>)

[PDF](<https://arxiv.org/pdf/1902.06894.pdf>)
