# Online Adversarial Attacks

Source: [Online Adversarial Attacks](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31bd0>)

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

Data updated: 2025-10-26T00:02:49.336Z

Authors: Andjela Mladenovic, Avishek Joey Bose, Hugo Berard, William L. Hamilton, Simon Lacoste-Julien, Pascal Vincent, Gauthier Gidel

Published: 2021-03-02T20:36:04.000Z

## Abstract

Adversarial attacks expose important vulnerabilities of deep learning models, yet little attention has been paid to settings where data arrives as a stream. In this paper, we formalize the online adversarial attack problem, emphasizing two key elements found in real-world use-cases: attackers must operate under partial knowledge of the target model, and the decisions made by the attacker are irrevocable since they operate on a transient data stream. We first rigorously analyze a deterministic variant of the online threat model by drawing parallels to the well-studied $k$-secretary problem in theoretical computer science and propose Virtual+, a simple yet practical online algorithm. Our main theoretical result shows Virtual+ yields provably the best competitive ratio over all single-threshold algorithms for $k\<5$ -- extending the previous analysis of the $k$-secretary problem. We also introduce the \\textit{stochastic $k$-secretary} -- effectively reducing online blackbox transfer attacks to a $k$-secretary problem under noise -- and prove theoretical bounds on the performance of Virtual+ adapted to this setting. Finally, we complement our theoretical results by conducting experiments on MNIST, CIFAR-10, and Imagenet classifiers, revealing the necessity of online algorithms in achieving near-optimal performance and also the rich interplay between attack strategies and online attack selection, enabling simple strategies like FGSM to outperform stronger adversaries.

## 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/2103.02014>)

[PDF](<https://arxiv.org/pdf/2103.02014.pdf>)
