arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.13536cs.ET
收藏

二进制神经网络的鲁棒性验证:一种Ising和量子启发框架

Robustness Verification of Binary Neural Networks: An Ising and Quantum-Inspired Framework

University of California, Santa Barbara(加州大学圣塔芭芭拉分校)

Rahul Singh, Seyran Saeedi, Zheng Zhang

AI总结:

本文提出一种受Ising和量子启发的框架,用于验证二进制神经网络对对抗攻击的鲁棒性,通过转换为QUBO问题并利用量子计算技术实现。

摘要:

二进制神经网络(BNNs)由于其低硬件复杂度和高能效,越来越多地应用于边缘计算应用。然而,验证BNNs对输入扰动(包括对抗攻击)的鲁棒性仍然具有计算挑战性,因为底层决策问题本质上是组合的。在本文中,我们提出了一种受Ising和量子启发的框架,用于BNN鲁棒性验证。我们证明,对于广泛类别的BNN架构,鲁棒性验证可以表述为二次约束布尔优化(QCBO)问题,并随后转换为可由Ising和量子启发求解器解决的二次无约束布尔优化(QUBO)实例。我们通过在二值化MNIST上求解所得到的QUBO来展示这种表述的可行性,使用自由能机(FEM)求解器和模拟退火。我们还展示了该框架在量子退火和数字退火平台上的部署。我们的结果突显了量子启发计算和Ising计算作为可信AI系统途径的潜力。

英文摘要:

Binary neural networks (BNNs) are increasingly deployed in edge computing applications due to their low hardware complexity and high energy efficiency. However, verifying the robustness of BNNs against input perturbations, including adversarial attacks, remains computationally challenging because the underlying decision problem is inherently combinatorial. In this paper, we propose an Ising- and quantum-inspired framework for BNN robustness verification. We show that, for a broad class of BNN architectures, robustness verification can be formulated as a Quadratic Constrained Boolean Optimization (QCBO) problem and subsequently transformed into a Quadratic Unconstrained Boolean Optimization (QUBO) instance amenable to Ising and quantum-inspired solvers. We demonstrate the feasibility of this formulation on binarized MNIST by solving the resulting QUBOs with a free energy machine (FEM) solver and simulated annealing. We also show the deployment of this framework on quantum annealing and digital annealing platforms. Our results highlight the potential of quantum-inspired computing and Ising computing as a pathway toward trustworthy AI systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑