mlsanityData to 14 Oct 2026

Data-Efficient Backdoor Attacks

arXiv 2204.12281 ↗First posted 22 Apr 2022cs.CV cs.AI cs.CRcited by 13

Not on the map. Why?

Abstract (arXiv)

Recent studies have proven that deep neural networks are vulnerable to backdoor attacks. Specifically, by mixing a small number of poisoned samples into the training set, the behavior of the trained model can be maliciously controlled. Existing attack methods construct such adversaries by randomly selecting some clean data from the benign set and then embedding a trigger into them. However, this selection strategy ignores the fact that each poisoned sample contributes inequally to the backdoor injection, which reduces the efficiency of poisoning. In this paper, we formulate improving the poisoned data efficiency by the selection as an optimization problem and propose a Filtering-and-Updating Strategy (FUS) to solve it. The experimental results on CIFAR-10 and ImageNet-10 indicate that the proposed method is effective: the same attack success rate can be achieved with only 47% to 75% of the poisoned sample volume compared to the random selection strategy. More importantly, the adversaries selected according to one setting can generalize well to other settings, exhibiting strong transferability. The prototype code of our method is now available at https://github.com/xpf/Data-Efficient-Backdoor-Attacks.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 21 of its 35 references that are in the map. First posted on arXiv 22 Apr 2022.

Builds on

21 of 35 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  6. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  7. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  8. 2018An Empirical Study of Example Forgetting during Deep Neural Network Learningcited by 678
  9. 2020Backdoor Learning: A Surveycited by 426
  10. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 349
  11. 2020Weight Poisoning Attacks on Pre-trained Modelscited by 341
  12. 2018Not All Samples Are Created Equal: Deep Learning with Importance Samplingcited by 328
9 more
  1. 2019Label-Consistent Backdoor Attackscited by 296
  2. 2018Knockoff Nets: Stealing Functionality of Black-Box Modelscited by 292
  3. 2018Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbationcited by 134
  4. 2019TBT: Targeted Neural Network Attack with Bit Trojancited by 113
  5. 2019Bypassing Backdoor Detection Algorithms in Deep Learningcited by 74
  6. 2018Backdooring Convolutional Neural Networks via Targeted Weight Perturbationscited by 69
  7. 2020Stop-and-Go: Exploring Backdoor Attacks on Deep Reinforcement Learning-based Traffic Congestion Control Systemscited by 37
  8. 2022A Comprehensive Survey on Data-Efficient GANs in Image Generationcited by 20
  9. 2021Enhancing Backdoor Attacks with Multi-Level MMD Regularizationcited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 4; 2025: 0; 2026: 1.

13 papers.

Sort:

By area:

  1. 2023Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspectivecited by 20
  2. 2024Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attackscited by 18
  3. 2023Beating Backdoor Attack at Its Own Gamecited by 11
  4. 2023Demystifying Poisoning Backdoor Attacks from a Statistical Perspectivecited by 10
  5. 2023Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarioscited by 7
  6. 2023Explore the Effect of Data Selection on Poison Efficiency in Backdoor Attackscited by 7
  7. 2023A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attackscited by 5
  8. 2023Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategycited by 5
  9. 2024Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attackscited by 4
  10. 2023Efficient Trigger Word Insertioncited by 2
  11. 2024Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attackscited by 2
  12. 2024Backdoor Attack with Mode Mixture Latent Modificationcited by 0
1 more
  1. 2026When Stronger Triggers Backfire: A High-Dimensional Theory of Backdoor Attackscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Mitigating Backdoors within Deep Neural Networks in Data-limited Configuration
  2. 2021Anti-Backdoor Learning: Training Clean Models on Poisoned Data
  3. 2023Stealthy Backdoor Attack via Confidence-driven Sampling
  4. 2021Excess Capacity and Backdoor Poisoning
  5. 2022Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain
  6. 2023Progressive Poisoned Data Isolation for Training-time Backdoor Defense
  7. 2025A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers
  8. 2024A Practical Trigger-Free Backdoor Attack on Neural Networks ↗