mlsanityData to 7 Oct 2026

Hard-label based Small Query Black-box Adversarial Attack

arXiv 2403.06014 ↗First posted 9 Mar 2024cs.LG cs.AI cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

We consider the hard label based black box adversarial attack setting which solely observes predicted classes from the target model. Most of the attack methods in this setting suffer from impractical number of queries required to achieve a successful attack. One approach to tackle this drawback is utilising the adversarial transferability between white box surrogate models and black box target model. However, the majority of the methods adopting this approach are soft label based to take the full advantage of zeroth order optimisation. Unlike mainstream methods, we propose a new practical setting of hard label based attack with an optimisation process guided by a pretrained surrogate model. Experiments show the proposed method significantly improves the query efficiency of the hard label based black-box attack across various target model architectures. We find the proposed method achieves approximately 5 times higher attack success rate compared to the benchmarks, especially at the small query budgets as 100 and 250.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 26 of its 32 references that are in the map. First posted on arXiv 9 Mar 2024.

Builds on

26 of 32 references.

References · 26

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  5. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  6. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  7. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  8. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  9. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  10. 2019On Evaluating Adversarial Robustnesscited by 442
  11. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
  12. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
14 more
  1. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 352
  2. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  3. 2019Simple Black-box Adversarial Attackscited by 249
  4. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
  5. 2017The Space of Transferable Adversarial Examplescited by 156
  6. 2018Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priorscited by 145
  7. 2018AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networkscited by 137
  8. 2019Sign-OPT: A Query-Efficient Hard-label Adversarial Attackcited by 118
  9. 2020QEBA: Query-Efficient Boundary-Based Blackbox Attackcited by 103
  10. 2019Black-Box Adversarial Attack with Transferable Model-based Embeddingcited by 57
  11. 2018Guessing Smart: Biased Sampling for Efficient Black-Box Adversarial Attackscited by 46
  12. 2022Query-Efficient Black-box Adversarial Attacks Guided by a Transfer-based Priorcited by 38
  13. 2020Learning Black-Box Attackers with Transferable Priors and Query Feedbackcited by 32
  14. 2020Adversarial Eigen Attack on Black-Box Modelscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 6; 2026: 1.

10 papers.

  1. 2024Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectorycited by 35
  2. 2024Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attackcited by 18
  3. 2025GreedyPixel: Fine-Grained Black-Box Adversarial Attack Via Greedy Algorithmcited by 3
  4. 2025Light as Deception: GPT-driven Natural Relighting Against Vision-Language Pre-training Modelscited by 1
  5. 2025Boosting Ray Search Procedure of Hard-label Attacks with Transfer-based Priorscited by 1
  6. 2025Constraint-Aware Flow Matching via Randomized Explorationcited by 1
  7. 2025ZQBA: Zero Query Black-box Adversarial Attackcited by 1
  8. 2024Counter-Samples: A Stateless Strategy to Neutralize Black Box Adversarial Attackscited by 0
  9. 2025Improving the Convergence Rate of Ray Search Optimization for Query-Efficient Hard-Label Attackscited by 0
  10. 2026Contract And Conquer: How to Provably Compute Adversarial Examples for a Black-Box Model?cited by 0