pith. sign in

arxiv: 2412.09450 · v1 · pith:GM5VEUNX · submitted 2024-12-12 · cs.CR

A Semi Black-Box Adversarial Bit-Flip Attack with Limited DNN Model Information

pith:GM5VEUNXopen to challenge →

classification cs.CR
keywords b3fabit-flipmodeladversarialadversaryattackdnnslimited
0
0 comments X
read the original abstract

Despite the rising prevalence of deep neural networks (DNNs) in cyber-physical systems, their vulnerability to adversarial bit-flip attacks (BFAs) is a noteworthy concern. This paper proposes B3FA, a semi-black-box BFA-based parameter attack on DNNs, assuming the adversary has limited knowledge about the model. We consider practical scenarios often feature a more restricted threat model for real-world systems, contrasting with the typical BFA models that presuppose the adversary's full access to a network's inputs and parameters. The introduced bit-flip approach utilizes a magnitude-based ranking method and a statistical re-construction technique to identify the vulnerable bits. We demonstrate the effectiveness of B3FA on several DNN models in a semi-black-box setting. For example, B3FA could drop the accuracy of a MobileNetV2 from 69.84% to 9% with only 20 bit-flips in a real-world setting.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.