Poster
Recovering the input of neural networks via single shot side-channel attacks
Lejla Batina (Radboud Universiteit Nijmegen)
Shivam Bhasin (Nanyang Technological University)
Dirmanto Jap (Nanyang Technological University)
Stjepan Picek (TU Delft - Cyber Security)
More Info
expand_more
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.
No files available
Metadata only record. There are no files for this record.