Y
Yansong Gao
Researcher at Nanjing University of Science and Technology
Publications - 87
Citations - 1897
Yansong Gao is an academic researcher from Nanjing University of Science and Technology. The author has contributed to research in topics: Computer science & Physical unclonable function. The author has an hindex of 14, co-authored 65 publications receiving 986 citations. Previous affiliations of Yansong Gao include University of Adelaide & Cooperative Research Centre.
Papers
More filters
Proceedings ArticleDOI
STRIP: a defence against trojan attacks on deep neural networks
TL;DR: This work builds STRong Intentional Perturbation (STRIP) based run-time trojan attack detection system and focuses on vision system, which achieves an overall false acceptance rate (FAR) of less than 1%, given a preset false rejection rate (FRR) of 1%, for different types of triggers.
Journal ArticleDOI
Physical unclonable functions
TL;DR: The development of physical unclonable functions, which exploit inherent randomness to give a physical entity a unique ‘fingerprint’ or trust anchor, are reviewed, considering the various potential applications of these devices and the security issues that they must confront.
Journal ArticleDOI
Emerging Physical Unclonable Functions With Nanotechnology
TL;DR: Initial research in this area aims to provide security primitives for emerging integrated circuits with nanotechnology, and to review emerging nanotechnology-based PUFs.
Journal ArticleDOI
Memristive crypto primitive for building highly secure physical unclonable functions.
TL;DR: This paper exploits the extremely large information density available in nanocrossbar architectures and the significant resistance variations of memristors to develop an on-chip memristive device based strong PUF (mrSPUF), which demonstrates desirable characteristics of PUFs, including uniqueness, reliability, and large number of challenge-response pairs (CRPs).
Posted Content
STRIP: A Defence Against Trojan Attacks on Deep Neural Networks
TL;DR: STRIP as mentioned in this paper is a run-time trojan attack detection system based on adversarial perturbation, which intentionally perturbs the incoming input, for instance by superimposing various image patterns, and observe the randomness of predicted classes for perturbed inputs from a given deployed model.