mlsanityData to 7 Oct 2026

SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images

arXiv 2407.11073 ↗First posted 13 Jul 2024cs.CR cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Adversarial attack has garnered considerable attention due to its profound implications for the secure deployment of robots in sensitive security scenarios. To potentially push for advances in the field, this paper studies the adversarial attack in the black-box setting and proposes an unlabeled data-driven adversarial attack method, called SemiAdv. Specifically, SemiAdv achieves the following breakthroughs compared with previous works. First, by introducing the semi-supervised learning technique into the adversarial attack, SemiAdv substantially decreases the number of queries required for generating adversarial samples. On average, SemiAdv only needs to query a few hundred times to launch an effective attack with more than 90% success rate. Second, many existing black-box adversarial attacks require massive labeled data to mitigate the difference between the local substitute model and the remote target model for a good attack performance. While SemiAdv relaxes this limitation and is capable of utilizing unlabeled raw data to launch an effective attack. Finally, our experiments show that SemiAdv saves up to 12x query accesses for generating adversarial samples while maintaining a competitive attack success rate compared with state-of-the-art attacks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 39 references that are in the map. First posted on arXiv 13 Jul 2024.

Builds on

29 of 39 references.

References · 29

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  4. 2016Adversarial examples in the physical worldcited by 1,762
  5. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  7. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  8. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  9. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  10. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  11. 2019Label Propagation for Deep Semi-supervised Learningcited by 287
  12. 2015DeepDriving: Learning Affordance for Direct Perception in Autonomous Drivingcited by 229
17 more
  1. 2017The Space of Transferable Adversarial Examplescited by 156
  2. 2018AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networkscited by 137
  3. 2019Sign-OPT: A Query-Efficient Hard-label Adversarial Attackcited by 118
  4. 2019Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learningcited by 103
  5. 2019NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networkscited by 94
  6. 2018GenAttack: Practical Black-box Attacks with Gradient-Free Optimizationcited by 82
  7. 2019A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Modelscited by 68
  8. 2020DaST: Data-free Substitute Training for Adversarial Attackscited by 60
  9. 2020SurFree: a fast surrogate-free black-box attackcited by 59
  10. 2018Guessing Smart: Biased Sampling for Efficient Black-Box Adversarial Attackscited by 46
  11. 2020Interpolation-based semi-supervised learning for object detectioncited by 40
  12. 2019Hybrid Batch Attacks: Finding Black-box Adversarial Examples with Limited Queriescited by 33
  13. 2019On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Methodcited by 21
  14. 2020Simple and Efficient Hard Label Black-box Adversarial Attacks in Low Query Budget Regimescited by 17
  15. 2018Query-Efficient Black-Box Attack by Active Learningcited by 15
  16. 2023On the Robustness of Split Learning against Adversarial Attackscited by 6
  17. 2022Enhance transferability of adversarial examples with model architecturecited by 4

Built on by

Not cited yet.