R
Robin Doss
Researcher at Deakin University
Publications - 172
Citations - 1888
Robin Doss is an academic researcher from Deakin University. The author has contributed to research in topics: Computer science & Authentication. The author has an hindex of 18, co-authored 143 publications receiving 1303 citations. Previous affiliations of Robin Doss include Chang'an University & IBM.
Papers
More filters
Book ChapterDOI
IoT Insider Attack - Survey
TL;DR: IoT attacks and the relevant technologies associated along with machine learning strategies that exist to overcome those obstacles are explored.
Journal ArticleDOI
A Secure Federated Learning Framework for Residential Short Term Load Forecasting
Muhammad Akbar Husnoo,Adnan Anwar,Nasser Hosseinzadeh,Shama Naz Islam,Abdun Naser Mahmood,Robin Doss +5 more
TL;DR: This work develops a state-of- the-art differentially private secured FL-based framework that ensures the privacy of the individual smart meter’s data while protect the security of FL models and architecture and outperforms conventional Fed-SGD models.
Journal ArticleDOI
Weak-Key Analysis for BIKE Post-Quantum Key Encapsulation Mechanism
Mohammad Reza Nosouhi,Syed Waleed Shah,Lei Pan,Yevhen Zolotavkin,Ashish Nanda,Praveen Gauravaram,Robin Doss +6 more
TL;DR: It is shown that the weak-keys can be a potential threat to IND-CCA security of the BIKE scheme and thus need attention from the research community prior to standardization, and a key-check algorithm is proposed that can potentially supplement the BIke mechanism and prevent users from generating and adopting weak keys.
BookDOI
Future network systems and security : second International Conference, FNSS 2016, Paris, France, November 23-25, 2016, Proceedings
TL;DR: Results show that the AuthentIx system can successfully detect anonymous and impersonated attackers, and furthermore, can be used as a general framework to cope with new anonymization and hiding techniques.
Posted Content
A Bytecode-based Approach for Smart Contract Classification
TL;DR: Wang et al. as discussed by the authors proposed a classification model based on features from contract bytecode instead of source code to solve the problem of adversarial attacks. And they also used feature selection and ensemble learning to optimize the model.