mlsanityData to 14 Oct 2026

Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning

arXiv 2109.08868 ↗First posted 18 Sep 2021cs.CV cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

A backdoored deep hashing model is expected to behave normally on original query images and return the images with the target label when a specific trigger pattern presents. To this end, we propose the confusing perturbations-induced backdoor attack (CIBA). It injects a small number of poisoned images with the correct label into the training data, which makes the attack hard to be detected. To craft the poisoned images, we first propose the confusing perturbations to disturb the hashing code learning. As such, the hashing model can learn more about the trigger. The confusing perturbations are imperceptible and generated by optimizing the intra-class dispersion and inter-class shift in the Hamming space. We then employ the targeted adversarial patch as the backdoor trigger to improve the attack performance. We have conducted extensive experiments to verify the effectiveness of our proposed CIBA. Our code is available at https://github.com/KuofengGao/CIBA.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 28 of its 61 references that are in the map. First posted on arXiv 18 Sep 2021.

Builds on

28 of 61 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  6. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  7. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 580
  8. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 499
  9. 2020Backdoor Learning: A Surveycited by 426
  10. 2019Hidden Trigger Backdoor Attackscited by 371
  11. 2020Invisible Backdoor Attack with Sample-Specific Triggerscited by 353
  12. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 349
16 more
  1. 2020Input-Aware Dynamic Backdoor Attackcited by 313
  2. 2019Label-Consistent Backdoor Attackscited by 296
  3. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 191
  4. 2020Clean-Label Backdoor Attacks on Video Recognition Modelscited by 169
  5. 2015Particular object retrieval with integral max-pooling of CNN activationscited by 161
  6. 2017HashNet: Deep Learning to Hash by Continuationcited by 122
  7. 2020Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attackscited by 116
  8. 2019Robust Anomaly Detection and Backdoor Attack Detection Via Differential Privacycited by 95
  9. 2015Feature Learning based Deep Supervised Hashing with Pairwise Labelscited by 59
  10. 2021Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bitscited by 49
  11. 2015Simultaneous Feature Learning and Hash Coding with Deep Neural Networkscited by 44
  12. 2020Targeted Attack for Deep Hashing based Retrievalcited by 35
  13. 2021PointBA: Towards Backdoor Attacks in 3D Point Cloudcited by 35
  14. 2020Open-sourced Dataset Protection via Backdoor Watermarkingcited by 30
  15. 2021Joint Face Image Restoration and Frontalization for Recognitioncited by 18
  16. 2021Contrastive Quantization with Code Memory for Unsupervised Image Retrievalcited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 5; 2025: 3; 2026: 1.

12 papers.

  1. 2023BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIPcited by 67
  2. 2024Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attackcited by 28
  3. 2023GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrievalcited by 20
  4. 2024PointNCBW: Towards Dataset Ownership Verification for Point Clouds via Negative Clean-label Backdoor Watermarkcited by 20
  5. 2025DarkHash: A Data-Free Backdoor Attack Against Deep Hashingcited by 6
  6. 2023Influencer Backdoor Attack on Semantic Segmentationcited by 5
  7. 2024Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformerscited by 5
  8. 2024Efficient Self-Supervised Video Hashing with Selective State Spacescited by 3
  9. 2025Pre-training CLIP against Data Poisoning with Optimal Transport-based Matching and Alignmentcited by 3
  10. 2024One Pixel is All I Needcited by 0
  11. 2025Clean Image May be Dangerous: Data Poisoning Attacks Against Deep Hashingcited by 0
  12. 2026Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label
  2. 2023Label Poisoning is All You Need
  3. 2024Countering Backdoor Attacks in Image Recognition: A Survey and Evaluation of Mitigation Strategies
  4. 2025DiffHash: Text-Guided Targeted Attack via Diffusion Models against Deep Hashing Image Retrieval
  5. 2024Clean-Label Physical Backdoor Attacks with Data Distillation
  6. 2023Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger
  7. 2024Clean-image Backdoor Attacks
  8. 2024Poisoning-based Backdoor Attacks for Arbitrary Target Label with Positive Triggers