Poster : recovering the input of neural networks via single shot side-channel attacks

Poster : recovering the input of neural networks via single shot side-channel attacks

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 attacke...

Full description

Saved in:
Bibliographic Details
Main Authors: Batina, Lejla, Jap, Dirmanto, Bhasin, Shivam, Picek, Stjepan
Other Authors: Conference on Computer and Communications Security (CCS 2019)
Format: Conference or Workshop Item
Language:English
Published: 2021
Subjects:
Science::Mathematics::Discrete mathematics::Cryptography
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Neural Networks
Side-channel Analysis
Online Access:https://hdl.handle.net/10356/148356
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-148356
record_format dspace
spelling sg-ntu-dr.10356-1483562021-08-10T05:39:28Z Poster : recovering the input of neural networks via single shot side-channel attacks Batina, Lejla Jap, Dirmanto Bhasin, Shivam Picek, Stjepan Conference on Computer and Communications Security (CCS 2019) Temasek Laboratories @ NTU Science::Mathematics::Discrete mathematics::Cryptography Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Neural Networks Side-channel Analysis 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. National Research Foundation (NRF) This research is supported by the Singapore National Research Foundation under its National Cybersecurity R&D Grant (“Cyber- Hardware Forensics & Assurance Evaluation R&D Programme” grant NRF2018–NCR–NCR009–0001 2021-08-10T05:39:28Z 2021-08-10T05:39:28Z 2019 Conference Paper 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 9781450367479 https://hdl.handle.net/10356/148356 10.1145/3319535.3363280 2-s2.0-85075935269 2657 2659 en NRF2018–NCR–NCR009–0001 © 2019 The Owner/Author(s). All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Science::Mathematics::Discrete mathematics::Cryptography
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Neural Networks
Side-channel Analysis
spellingShingle Science::Mathematics::Discrete mathematics::Cryptography
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Neural Networks
Side-channel Analysis
Batina, Lejla
Jap, Dirmanto
Bhasin, Shivam
Picek, Stjepan
Poster : recovering the input of neural networks via single shot side-channel attacks
description 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.
author2 Conference on Computer and Communications Security (CCS 2019)
author_facet Conference on Computer and Communications Security (CCS 2019)
Batina, Lejla
Jap, Dirmanto
Bhasin, Shivam
Picek, Stjepan
format Conference or Workshop Item
author Batina, Lejla
Jap, Dirmanto
Bhasin, Shivam
Picek, Stjepan
author_sort Batina, Lejla
title Poster : recovering the input of neural networks via single shot side-channel attacks
title_short Poster : recovering the input of neural networks via single shot side-channel attacks
title_full Poster : recovering the input of neural networks via single shot side-channel attacks
title_fullStr Poster : recovering the input of neural networks via single shot side-channel attacks
title_full_unstemmed Poster : recovering the input of neural networks via single shot side-channel attacks
title_sort poster : recovering the input of neural networks via single shot side-channel attacks
publishDate 2021
url https://hdl.handle.net/10356/148356
_version_ 1709685323516084224

Similar Items