mlsanityData to 7 Oct 2026

Targeted Mismatch Adversarial Attack: Query with a Flower to Retrieve the Tower

arXiv 1908.09163 ↗First posted 24 Aug 2019cs.CVcited by 26

Not on the map. Why?

Abstract (arXiv)

Access to online visual search engines implies sharing of private user content - the query images. We introduce the concept of targeted mismatch attack for deep learning based retrieval systems to generate an adversarial image to conceal the query image. The generated image looks nothing like the user intended query, but leads to identical or very similar retrieval results. Transferring attacks to fully unseen networks is challenging. We show successful attacks to partially unknown systems, by designing various loss functions for the adversarial image construction. These include loss functions, for example, for unknown global pooling operation or unknown input resolution by the retrieval system. We evaluate the attacks on standard retrieval benchmarks and compare the results retrieved with the original and adversarial image.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 5; 2023: 5; 2024: 2; 2025: 1; 2026: 4.

26 papers.

Sort:

By area:

  1. 2023Poisoning Retrieval Corpora by Injecting Adversarial Passagescited by 153
  2. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  3. 2021Deep Learning for Instance Retrieval: A Surveycited by 70
  4. 2021Person Re-identification Method Based on Color Attack and Joint Defencecited by 56
  5. 2021The 2021 Image Similarity Dataset and Challengecited by 44
  6. 2023A Survey on Transferability of Adversarial Examples across Deep Neural Networkscited by 43
  7. 2024Corpus Poisoning via Approximate Greedy Gradient Descentcited by 21
  8. 2021Multi-Expert Adversarial Attack Detection in Person Re-identification Using Context Inconsistencycited by 12
  9. 2022Enhancing Adversarial Robustness for Deep Metric Learningcited by 10
  10. 2021Practical Relative Order Attack in Deep Rankingcited by 9
  11. 2021Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashingcited by 8
  12. 2021Adversarial Attack and Defense in Deep Rankingcited by 8
14 more
  1. 2021Discriminator-Free Generative Adversarial Attackcited by 8
  2. 2022Active Image Indexingcited by 8
  3. 2022MORA: Improving Ensemble Robustness Evaluation with Model-Reweighing Attackcited by 7
  4. 2023OMG-ATTACK: Self-Supervised On-Manifold Generation of Transferable Evasion Attackscited by 2
  5. 2023Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrievalcited by 2
  6. 2022ARIA: Adversarially Robust Image Attribution for Content Provenancecited by 1
  7. 2024Learning to Learn Transferable Generative Attack for Person Re-Identificationcited by 1
  8. 2025Task-Agnostic Attacks Against Vision Foundation Modelscited by 1
  9. 2022Advancing Deep Metric Learning Through Multiple Batch Norms And Multi-Targeted Adversarial Examplescited by 0
  10. 2023Robust Ranking Explanationscited by 0
  11. 2026Dummy-Aware Weighted Attack (DAWA): Breaking the Safe Sink in Dummy Class Defensescited by 0
  12. 2026Adversarial Attacks on Robot Localization Systems via Deep Feature Perturbationcited by 0
  13. 2026Toward Trustworthy AI: Multi-Target Adversarial Attacks and Robust Defenses for Continuous Data Summarizationcited by 0
  14. 2026The Role of Input Dimensionality in the Emergence and Targeted Control of Adversarial Examplescited by 0