Analyzing the Impact of Bit-Flip Attacks on Extreme Learning Machine for Age-related Macular Degeneration Detection on OCT Volumes

Cheng-Hsi Yang, Li-Zhe Liu,Cheng-Hung Lin,Cheng-Kai Lu,Tzu-Lun Huang,Jia-Kang Wang

2024 IEEE International Symposium on Consumer Technology (ISCT)（2024）

Cited 0|Views3

Abstract

In recent years, the Extreme Learning Machine (ELM) architecture has been widely applied in various fields, leading to an increase in hardware attack attempts. However, the security challenges of ELM weights have not been thoroughly studied. This study investigates the impact of bit-flip attacks (BFA) on ELM, focusing on the different weights and the importance of each bit position within these weights. We employed two strategies: random BFA and indexed random BFA. These attacks were used to assess their effects on the accuracy of ELM models. In the random BFA, attacking the input weight caused a 1.87% accuracy drop for each bit attacked. Attacking the output weight resulted in a 50.44 % accuracy drop after five bits were attacked. Based on the indexed random BFA results, we recommend protecting the first seven bits of the input weight and the first twenty bits of the output weight.

Translated text

Key words

Hardware Security,Extreme Learning Machines (ELM),Bit-Flip Attacks (BFA),Fault Injection Attacks

求助PDF

上传PDF

Bibtex

AI Read Science

AI Summary

AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.

Example

Background

Key content

Introduction

Methods

Results

Related work

Fund

Key content

Pretraining has recently greatly promoted the development of natural language processing (NLP)
We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance

Upload PDF to Generate Summary

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper

Data Disclaimer

The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn

Chat Paper

【要点】：本文研究了位翻转攻击对极端学习机（ELM）在年龄相关性黄斑变性检测中的应用影响，并提出保护权重中关键位的策略。

【方法】：采用随机位翻转攻击（BFA）和索引随机位翻转攻击两种策略，分析不同权重位对模型准确性的影响。

【实验】：通过在OCT体积数据集上实施攻击，发现输入权重每位被攻击导致准确度下降1.87%，输出权重五位被攻击后准确度下降50.44%，推荐保护输入权重的前七位和输出权重的前二十位。