Library
Repository Home account_circle Login

Poster

Recovering the input of neural networks via single shot side-channel attacks

Conference Paper (2019)
Author(s)

Lejla Batina (Radboud Universiteit Nijmegen)

Shivam Bhasin (Nanyang Technological University)

Dirmanto Jap (Nanyang Technological University)

Stjepan Picek (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Research Group
Cyber Security
DOI related publication
https://doi.org/10.1145/3319535.3363280 Final published version
More Info
expand_more
Publication Year
2019
Language
English
Research Group
Cyber Security
Pages (from-to)
2657-2659
ISBN (electronic)
978-1-4503-6747-9
Event
26th ACM SIGSAC Conference on Computer and Communications Security, CCS 2019 (2019-11-11 - 2019-11-15), London, United Kingdom
Downloads counter
177

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.