I know what you trained last summer: A survey on stealing machine learning models and defences

D Oliynyk, R Mayer, A Rauber - ACM Computing Surveys, 2023 - dl.acm.org
Machine-Learning-as-a-Service (MLaaS) has become a widespread paradigm, making
even the most complex Machine Learning models available for clients via, eg, a pay-per …

Adversarial machine learning in wireless communications using RF data: A review

D Adesina, CC Hsieh, YE Sagduyu… - … Surveys & Tutorials, 2022 - ieeexplore.ieee.org
Machine learning (ML) provides effective means to learn from spectrum data and solve
complex tasks involved in wireless communications. Supported by recent advances in …

Deep learning for launching and mitigating wireless jamming attacks

T Erpek, YE Sagduyu, Y Shi - IEEE Transactions on Cognitive …, 2018 - ieeexplore.ieee.org
An adversarial machine learning approach is introduced to launch jamming attacks on
wireless communications and a defense strategy is presented. A cognitive transmitter uses a …

Deep learning for wireless communications

T Erpek, TJ O'Shea, YE Sagduyu, Y Shi… - … and Analysis of Deep …, 2020 - Springer
Existing communication systems exhibit inherent limitations in translating theory to practice
when handling the complexity of optimization for emerging wireless applications with high …

Generative Adversarial Networks (GANs) in networking: A comprehensive survey & evaluation

H Navidan, PF Moshiri, M Nabati, R Shahbazian… - Computer Networks, 2021 - Elsevier
Despite the recency of their conception, Generative Adversarial Networks (GANs) constitute
an extensively-researched machine learning sub-field for the creation of synthetic data …

Model extraction and adversarial transferability, your BERT is vulnerable!

X He, L Lyu, Q Xu, L Sun - arXiv preprint arXiv:2103.10013, 2021 - arxiv.org
Natural language processing (NLP) tasks, ranging from text classification to text generation,
have been revolutionised by the pre-trained language models, such as BERT. This allows …

Activethief: Model extraction using active learning and unannotated public data

S Pal, Y Gupta, A Shukla, A Kanade, S Shevade… - Proceedings of the AAAI …, 2020 - aaai.org
Abstract Machine learning models are increasingly being deployed in practice. Machine
Learning as a Service (MLaaS) providers expose such models to queries by third-party …

Applying generative machine learning to intrusion detection: A systematic mapping study and review

J Halvorsen, C Izurieta, H Cai… - ACM Computing …, 2024 - dl.acm.org
Intrusion Detection Systems (IDSs) are an essential element of modern cyber defense,
alerting users to when and where cyber-attacks occur. Machine learning can enable IDSs to …

An empirical survey on explainable ai technologies: Recent trends, use-cases, and categories from technical and application perspectives

M Nagahisarchoghaei, N Nur, L Cummins, N Nur… - Electronics, 2023 - mdpi.com
In a wide range of industries and academic fields, artificial intelligence is becoming
increasingly prevalent. AI models are taking on more crucial decision-making tasks as they …

IoT network security from the perspective of adversarial deep learning

YE Sagduyu, Y Shi, T Erpek - 2019 16th Annual IEEE …, 2019 - ieeexplore.ieee.org
Machine learning finds rich applications in Internet of Things (IoT) networks such as
information retrieval, traffic management, spectrum sensing, and signal authentication. While …