Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/148356
Title: Poster : recovering the input of neural networks via single shot side-channel attacks
Authors: Batina, Lejla
Jap, Dirmanto
Bhasin, Shivam
Picek, Stjepan
Keywords: Science::Mathematics::Discrete mathematics::Cryptography
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Issue Date: 2019
Source: Batina, L., Jap, D., Bhasin, S. & Picek, S. (2019). Poster : recovering the input of neural networks via single shot side-channel attacks. Conference on Computer and Communications Security (CCS 2019), 2657-2659. https://dx.doi.org/10.1145/3319535.3363280
Project: NRF2018–NCR–NCR009–0001
metadata.dc.contributor.conference: Conference on Computer and Communications Security (CCS 2019)
Abstract: The interplay between machine learning and security is becoming more prominent. New applications using machine learning also bring new security risks. Here, we show it is possible to reverse-engineer the inputs to a neural network with only a single-shot side-channel measurement assuming the attacker knows the neural network architecture being used.
URI: https://hdl.handle.net/10356/148356
ISBN: 9781450367479
DOI: 10.1145/3319535.3363280
Research Centres: Temasek Laboratories @ NTU 
Rights: © 2019 The Owner/Author(s). All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:TL Conference Papers

SCOPUSTM   
Citations 20

13
Updated on May 25, 2023

Web of ScienceTM
Citations 20

7
Updated on May 30, 2023

Page view(s)

230
Updated on Jun 1, 2023

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.