The Phantom Gradient Attack: A Study of Replacement Functions for the XOR Function

Åvald Åslaugson Sommervoll

Quality, Reliability, Security and Robustness in Heterogeneous Systems. 17th EAI International Conference, QShine 2021, Virtual Event, November 29–30, 2021, Proceedings

Research Article

The Phantom Gradient Attack: A Study of Replacement Functions for the XOR Function

Download

3 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1007/978-3-030-91424-0_14,
    author={\AE{}vald \AE{}slaugson Sommervoll},
    title={The Phantom Gradient Attack: A Study of Replacement Functions for the XOR Function},
    proceedings={Quality, Reliability, Security and Robustness in Heterogeneous Systems. 17th EAI International Conference, QShine 2021, Virtual Event, November 29--30, 2021, Proceedings},
    proceedings_a={QSHINE},
    year={2021},
    month={11},
    keywords={Phantom gradient attack Replacement function Neural network Neuro-cryptanalysis},
    doi={10.1007/978-3-030-91424-0_14}
}

Åvald Åslaugson Sommervoll
Year: 2021
The Phantom Gradient Attack: A Study of Replacement Functions for the XOR Function
QSHINE
Springer
DOI: 10.1007/978-3-030-91424-0_14

Åvald Åslaugson Sommervoll¹^,*

1: University of Oslo, Problemveien 7

*Contact email: aavalds@ifi.uio.no

Abstract

We build on the phantom gradient attack by introducing some new replacement function candidates for XOR. In this work, we put forward four new candidates’ replacement functions and investigate the impact of different learning rates. We also extend and investigate the new replacement functions power on bitwise rotation XOR, of which previous phantom gradient attack works have struggled.

Keywords: Phantom gradient attack Replacement function Neural network Neuro-cryptanalysis

Published: 2021-11-17
Appears in: SpringerLink

: http://dx.doi.org/10.1007/978-3-030-91424-0_14

The Phantom Gradient Attack: A Study of Replacement Functions for the XOR Function

Abstract

About EAI

Community

Publish with EAI