A survey of bit-flip attacks on deep neural network and corresponding defense methods

C Qian, M Zhang, Y Nie, S Lu, H Cao - Electronics, 2023 - mdpi.com
As the machine learning-related technology has made great progress in recent years, deep
neural networks are widely used in many scenarios, including security-critical ones, which …

Rowhammer Attacks in Dynamic Random-Access Memory and Defense Methods

D Kim, H Park, I Yeo, YK Lee, Y Kim, HM Lee… - Sensors, 2024 - mdpi.com
This paper provides a comprehensive overview of the security vulnerability known as
rowhammer in Dynamic Random-Access Memory (DRAM). While DRAM offers many …

A closer look at evaluating the bit-flip attack against deep neural networks

K Hector, PA Moëllic, M Dumont… - 2022 IEEE 28th …, 2022 - ieeexplore.ieee.org
Deep neural network models are massively deployed on a wide variety of hardware
platforms. This results in the appearance of new attack vectors that significantly extend the …

Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Leman Go Indifferent

L Kummer, S Moustafa, S Schrittwieser… - Proceedings of the 30th …, 2024 - dl.acm.org
Prior attacks on graph neural networks have focused on graph poisoning and evasion,
neglecting the network's weights and biases. For convolutional neural networks, however …