mlsanityData to 7 Oct 2026

Silent Killer: A Stealthy, Clean-Label, Black-Box Backdoor Attack

arXiv 2301.02615 ↗First posted 5 Jan 2023cs.CR cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Backdoor poisoning attacks pose a well-known risk to neural networks. However, most studies have focused on lenient threat models. We introduce Silent Killer, a novel attack that operates in clean-label, black-box settings, uses a stealthy poison and trigger and outperforms existing methods. We investigate the use of universal adversarial perturbations as triggers in clean-label attacks, following the success of such approaches under poison-label settings. We analyze the success of a naive adaptation and find that gradient alignment for crafting the poison is required to ensure high success rates. We conduct thorough experiments on MNIST, CIFAR10, and a reduced version of ImageNet and achieve state-of-the-art results.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 28 references that are in the map. First posted on arXiv 5 Jan 2023.

Builds on

23 of 28 references.

References · 23

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2016Adversarial examples in the physical worldcited by 1,762
  6. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  7. 2016Universal adversarial perturbationscited by 774
  8. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
  9. 2020Backdoor Learning: A Surveycited by 412
  10. 2019Hidden Trigger Backdoor Attackscited by 359
  11. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 341
  12. 2019Label-Consistent Backdoor Attackscited by 285
11 more
  1. 2019A new Backdoor Attack in CNNs by training set corruption without label poisoningcited by 237
  2. 2020Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defensescited by 171
  3. 2020Clean-Label Backdoor Attacks on Video Recognition Modelscited by 162
  4. 2018Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbationcited by 131
  5. 2022Narcissus: A Practical Clean-Label Backdoor Attack with Limited Informationcited by 102
  6. 2021Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratchcited by 98
  7. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
  8. 2020On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shapingcited by 82
  9. 2021DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentationscited by 33
  10. 2022Enhancing Clean Label Backdoor Attack with Two-phase Specific Triggerscited by 7
  11. 2022A Universal Adversarial Policy for Text Classifierscited by 1

Built on by

Not cited yet.