Papers › ZeBRA: Precisely Destroying Neural Networks with Zero-Data Based Repeated Bit Flip Attack

ZeBRA: Precisely Destroying Neural Networks with Zero-Data Based Repeated Bit Flip Attack

1 Nov 2021arXiv:2111.01080archive 2025-07-28

Dahoon Park, Kon-Woo Kwon, Sunghoon Im, Jaeha Kung

In this paper, we present Zero-data Based Repeated bit flip Attack (ZeBRA) that precisely destroys deep neural networks (DNNs) by synthesizing its own attack datasets. Many prior works on adversarial weight attack require not only the weight parameters, but also the training or test dataset in searching vulnerable bits to be attacked. We propose to synthesize the attack dataset, named distilled target data, by utilizing the statistics of batch normalization layers in the victim DNN model. Equipped with the distilled target data, our ZeBRA algorithm can search vulnerable bits in the model without accessing training or test dataset. Thus, our approach makes the adversarial weight attack more fatal to the security of DNNs. Our experimental results show that 2.0x (CIFAR-10) and 1.6x (ImageNet) less number of bit flips are required on average to destroy DNNs compared to the previous attack method. Our code is available at https://github. com/pdh930105/ZeBRA.

PaperPDFCode

Code

pdh930105/zebra officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Batch NormalizationFLIPTest

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections