可扩展的数字计算在内存Ising机器用于二进制神经网络鲁棒性验证
Scalable Digital Compute-in-Memory Ising Machines for Robustness Verification of Binary Neural Networks
AI总结:
本文提出利用数字计算在内存Ising机器将二进制神经网络鲁棒性验证转化为二次无约束二元优化问题,通过高效退火算法实现鲁棒性验证。
摘要:
二进制神经网络(BNN)鲁棒性验证是NP难问题,因为它可以被表述为一个组合搜索问题,寻找诱导误分类的对抗扰动。精确验证方法因此随着问题维度的增加而扩展性差,推动了使用硬件加速启发式方法和非传统计算平台(如Ising求解器)的使用,这些平台能够高效地探索复杂的能量景观并发现高质量的解决方案。在本工作中,我们将BNN鲁棒性验证重新表述为二次无约束二元优化(QUBO)问题,并使用基于SRAM的数字计算在内存(DCIM)Ising机器来解决。我们没有要求全局最优解,而是利用DCIM Ising机器产生的不完美解来提取对抗扰动,从而展示BNN的非鲁棒性。所提出的架构在大约9.1~Mb的SRAM中存储量化QUBO系数,并通过电压控制的伪读动态在内存中进行退火,使能够以最小的数据移动进行迭代更新。实验投影表明,所提出的方法相对于传统CPU实现,在收敛速率上实现了178倍的加速,在能效上提高了1538倍。
英文摘要:
Verification of binary neural network (BNN) robustness is NP-hard, as it can be formulated as a combinatorial search for an adversarial perturbation that induces misclassification. Exact verification methods therefore scale poorly with problem dimension, motivating the use of hardware-accelerated heuristics and unconventional computing platforms, such as Ising solvers, that can efficiently explore complex energy landscapes and discover high-quality solutions. In this work, we reformulate BNN robustness verification as a quadratic unconstrained binary optimization (QUBO) problem and solve it using a digital compute-in-memory (DCIM) SRAM-based Ising machine. Instead of requiring globally optimal solutions, we exploit imperfect solutions produced by the DCIM Ising machine to extract adversarial perturbations and thereby demonstrate the non-robustness of the BNN. The proposed architecture stores quantized QUBO coefficients in approximately 9.1~Mb of SRAM and performs annealing in memory via voltage-controlled pseudo-read dynamics, enabling iterative updates with minimal data movement. Experimental projections indicate that the proposed approach achieves a $178\times$ acceleration in convergence rate and a $1538\times$ improvement in power efficiency relative to conventional CPU-based implementations.
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。