The Weight of a Bit: EMFI Sensitivity Analysis of Embedded Deep Learning Models
TTControl GmbH(TTControl公司);Faculty of Informatics and Information Technologies, Slovak University of Technology(斯洛伐克理工大学信息学与信息技术学院);State Key Laboratory of Blockchain and Data Security, Zhejiang University(浙江大学区块链与数据安全国家重点实验室)
Fault injection attacks on embedded neural network models have been shown as a potent threat. Numerous works studied resilience of models from various points of view. As of now, there is no comprehensive study that would evaluate the influence of number representations used for model parameters against electromagnetic fault injection (EMFI) attacks.
In this paper, we investigate how four different number representations influence the success of an EMFI attack on embedded neural network models. We chose two common floating-point representations (32-bit, and 16-bit), and two integer representations (8-bit, and 4-bit). We deployed four common image classifiers, ResNet-18, ResNet-34, ResNet-50, and VGG-11, on an embedded memory chip, and utilized a low-cost EMFI platform to trigger faults. Beyond accuracy evaluation, we characterize the injected fault pattern by analyzing the bit error rate, the spatial distribution of corrupted bytes, and the prevalence of 0xFE/0xFF byte values across formats, identifying the mechanisms responsible for the observed differences in resilience.
Our results show that while floating-point representations exhibit almost a complete degradation in accuracy (Top-1 and Top-5) after a single fault injection, integer representations offer better resistance overall. In particular, the 8-bit representation on a relatively large network (VGG-11) retains Top-1 accuracy of around 70% and Top-5 at around 90%.
DeepNcode: Encoding-Based Protection against Bit-Flip Attacks on Neural Networks
Slovak University of Technology(斯洛伐克技术大学);Faculty of Informatics and Information Technologies(信息与信息技术学院);TTControl GmbH(TTControl有限公司);University of Novi Sad(诺威萨大学);Ethernal
Robust Emotion Recognition from Low Quality and Low Bit Rate Video: A Deep Learning Approach
Beckman Institute, University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校贝克曼研究所);Texas A&M University(德克萨斯A&M大学);University of Missouri, Kansas City(密苏里大学堪萨斯城分校);Snap Inc(Snap公司);University of Washington(华盛顿大学)
Adaptive Variation-Resilient Random Number Generator for Embedded Encryption
King Faisal University(费萨尔国王大学);University of California, Santa Barbara(加利福尼亚大学圣塔芭芭拉分校);Nanyang Technological University(南洋理工大学);Queen’s University(女王大学);Massachusetts Institute of Technology(麻省理工学院)