Adaptive neural recovery for highly robust brain-like representation
Adaptive neural recovery for highly robust brain-like representation
复制标题
DOI：
10.1145/3489517.3530659
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Prathyush P. Poduval;Yang Ni;Yeseong Kim;K. Ni;Raghavan Kumar;Rosario Cammarota;M. Imani
中科院分区：
文献类型：
--
作者：
Prathyush P. Poduval;Yang Ni;Yeseong Kim;K. Ni;Raghavan Kumar;Rosario Cammarota;M. Imani
当今的机器学习平台存在有关不安全和不可靠的内存系统的重大鲁棒性问题。在传统的数据表示中，由于噪声或攻击引起的位翻转可能会导致价值爆炸，从而导致学习预测不正确。在本文中，我们提出了RobusTHD，这是一种基于高维计算（HDC）的强大而耐噪声的学习系统，模仿了重要的大脑功能。与传统的二进制表示不同，Robusthd利用了冗余和全息表示，确保所有位对计算都有相同的影响。 Robusthd还提出了一个运行时框架，该框架以不受监督的方式适应地识别和再生有故障的维度。我们的解决方案不仅可以防止可能的位弹攻击，而且还提供了一种具有高度鲁棒性的学习解决方案。我们进行了从常规平台到新兴处理内存架构的互叠评估。我们的评估表明，RobusTHD低于10％的随机位翻转攻击，最多可提供0.53％的质量损失，而深度学习解决方案的准确性超过26.2％。
Today's machine learning platforms have major robustness issues dealing with insecure and unreliable memory systems. In conventional data representation, bit flips due to noise or attack can cause value explosion, which leads to incorrect learning prediction. In this paper, we propose RobustHD, a robust and noise-tolerant learning system based on HyperDimensional Computing (HDC), mimicking important brain functionalities. Unlike traditional binary representation, RobustHD exploits a redundant and holographic representation, ensuring all bits have the same impact on the computation. RobustHD also proposes a runtime framework that adaptively identifies and regenerates the faulty dimensions in an unsupervised way. Our solution not only provides security against possible bit-flip attacks but also provides a learning solution with high robustness to noises in the memory. We performed a cross-stacked evaluation from a conventional platform to emerging processing in-memory architecture. Our evaluation shows that under 10% random bit flip attack, RobustHD provides a maximum of 0.53% quality loss, while deep learning solutions are losing over 26.2% accuracy.