mlsanityData to 14 Oct 2026

Online Adversarial Attacks

arXiv 2103.02014 ↗First posted 2 Mar 2021cs.LG cs.CR cs.DScited by 3

Not on the map. Why?

Abstract (arXiv)

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 textitstochastic 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.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 35 of its 47 references that are in the map. First posted on arXiv 2 Mar 2021.

Builds on

35 of 47 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2016Densely Connected Convolutional Networkscited by 6,720
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  7. 2013Intriguing properties of neural networkscited by 5,155
  8. 2016Wide Residual Networkscited by 3,070
  9. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  10. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  11. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
  12. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 501
23 more
  1. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 460
  2. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 446
  3. 2018Adversarial Attacks and Defences: A Surveycited by 259
  4. 2018MMA Training: Direct Input Space Margin Maximization through Adversarial Trainingcited by 172
  5. 2017Tactics of Adversarial Attack on Deep Reinforcement Learning Agentscited by 166
  6. 2017The Space of Transferable Adversarial Examplescited by 158
  7. 2020Secretary and Online Matching Problems with Machine Learned Advicecited by 71
  8. 2020Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learningcited by 63
  9. 2019Black-box Adversarial Attacks on Video Recognition Modelscited by 58
  10. 2019Stateful Detection of Black-Box Adversarial Attackscited by 56
  11. 2017MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examplescited by 46
  12. 2020Secretaries with Advicecited by 41
  13. 2020Adversarial Example Gamescited by 34
  14. 2013Prophet Inequalities with Limited Informationcited by 13
  15. 2019Real-Time Adversarial Attackscited by 11
  16. 2019Competitive Analysis with a Sample and the Secretary Problemcited by 9
  17. 2019ReMASC: Realistic Replay Attack Corpus for Voice Controlled Systemscited by 7
  18. 2015Prophet Secretarycited by 6
  19. 2017Query-Efficient Black-box Adversarial Examples (superceded)cited by 5
  20. 2017Prophet Secretary: Surpassing the 1-1/e Barriercited by 4
  21. 2019Robust Algorithms for the Secretary Problemcited by 4
  22. 2020New Results for the k-Secretary Problemcited by 2
  23. 2020Improved Online Algorithms for Knapsack and GAP in the Random Order Modelcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 3.

3 papers.

  1. 2023Adversarial Learning in Real-World Fraud Detection: Challenges and Perspectivescited by 5
  2. 2023Provable Robustness for Streaming Models with a Sliding Windowcited by 1
  3. 2023Bridging Optimal Transport and Jacobian Regularization by Optimal Trajectory for Enhanced Adversarial Defensecited by 0