Abstract
Hardware faults can flip bits in the stored weights of a quantized neural network, potentially compromising its predictions. While such faults typically affect multiple parameters simultaneously, existing verifiers are limited to single-parameter perturbations due to the combinatorial explosion of possible flip locations in large networks. We present mBFV (m-BitFlip Verifier), an efficient verification framework that proves robustness against simultaneous bit flips across multiple parameters without explicitly enumerating these combinations. mBFV achieves this via a novel multi-parameter bound propagation technique that directly aggregates the m worst-case contributions. To further tighten these bounds, mBFV employs a branch-and-bound mechanism over perturbation locations, partitioning the potential flips to smaller groups of neurons. Evaluated on 625 instances, mBFV successfully verifies 293, significantly outperforming a prior single-parameter verifier (38 verified instances) and an exact mixed-integer linear programming baseline (0 verified instances). Notably, while these baselines are restricted to single-parameter flips on small networks (up to 13k parameters), mBFV scales to verify networks with up to 1.15M parameters against up to four simultaneous parameter flips.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Duong, H., Le, T., Nguyen, H., & Nguyen, T. (2026). Towards Verifying Neural Networks Against Multi-Parameter Bit-Flip Perturbations. https://omanscience.com/en/articles/towards-verifying-neural-networks-against-multi-parameter-bit-flip-perturbations
MLA 9
Duong, Hai, et al. "Towards Verifying Neural Networks Against Multi-Parameter Bit-Flip Perturbations." https://omanscience.com/en/articles/towards-verifying-neural-networks-against-multi-parameter-bit-flip-perturbations.
Chicago (author–date)
Duong, Hai, Thanh Le, Ho Nguyen, and ThanhVu Nguyen. 2026. "Towards Verifying Neural Networks Against Multi-Parameter Bit-Flip Perturbations." https://omanscience.com/en/articles/towards-verifying-neural-networks-against-multi-parameter-bit-flip-perturbations.
Harvard
Duong, H., Le, T., Nguyen, H. and Nguyen, T. (2026) 'Towards Verifying Neural Networks Against Multi-Parameter Bit-Flip Perturbations', Available at: https://omanscience.com/en/articles/towards-verifying-neural-networks-against-multi-parameter-bit-flip-perturbations.
Vancouver
Duong H, Le T, Nguyen H, Nguyen T. Towards Verifying Neural Networks Against Multi-Parameter Bit-Flip Perturbations. https://omanscience.com/en/articles/towards-verifying-neural-networks-against-multi-parameter-bit-flip-perturbations
IEEE
H. Duong, T. Le, H. Nguyen, and T. Nguyen, "Towards Verifying Neural Networks Against Multi-Parameter Bit-Flip Perturbations," https://omanscience.com/en/articles/towards-verifying-neural-networks-against-multi-parameter-bit-flip-perturbations.