mlsanityData to 14 Oct 2026

BDFA: A Blind Data Adversarial Bit-flip Attack on Deep Neural Networks

arXiv 2112.03477 ↗First posted 7 Dec 2021cs.CR cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Adversarial bit-flip attack (BFA) on Neural Network weights can result in catastrophic accuracy degradation by flipping a very small number of bits. A major drawback of prior bit flip attack techniques is their reliance on test data. This is frequently not possible for applications that contain sensitive or proprietary data. In this paper, we propose Blind Data Adversarial Bit-flip Attack (BDFA), a novel technique to enable BFA without any access to the training or testing data. This is achieved by optimizing for a synthetic dataset, which is engineered to match the statistics of batch normalization across different layers of the network and the targeted label. Experimental results show that BDFA could decrease the accuracy of ResNet50 significantly from 75.96% to 13.94% with only 4 bits flips.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 17 of its 30 references that are in the map. First posted on arXiv 7 Dec 2021.

Builds on

17 of 30 references.

References · 17

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  5. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  6. 2016Universal adversarial perturbationscited by 784
  7. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 521
  8. 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 269
  9. 2019Bit-Flip Attack: Crushing Neural Network with Progressive Bit Searchcited by 108
  10. 2020DeepHammer: Depleting the Intelligence of Deep Neural Networks through Targeted Chain of Bit Flipscited by 56
  11. 2021DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memoriescited by 42
  12. 2020Hermes Attack: Steal DNN Models with Lossless Inference Accuracycited by 41
5 more
  1. 2020Universal Adversarial Perturbations: A Surveycited by 28
  2. 2019Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networkscited by 26
  3. 2020SNIFF: Reverse Engineering of Neural Networks with Fault Attackscited by 23
  4. 2020T-BFA: Targeted Bit-Flip Adversarial Weight Attackcited by 4
  5. 2020DeepPeep: Exploiting Design Ramifications to Decipher the Architecture of Compact DNNscited by 3

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flipscited by 4

Similar, not cited

Close in wording, no citation either way

  1. 2023One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training
  2. 2021RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracy
  3. 2023Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces in DNN Executables
  4. 2024Impactful Bit-Flip Search on Full-precision Models
  5. 2024DeepNcode: Encoding-Based Protection against Bit-Flip Attacks on Neural Networks
  6. 2021Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits
  7. 2022Versatile Weight Attack via Flipping Limited Bits
  8. 2021RADAR: Run-time Adversarial Weight Attack Detection and Accuracy Recovery