I know what you trained last summer: A survey on stealing machine learning models and defences
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 …
even the most complex Machine Learning models available for clients via, eg, a pay-per …
Toward trustworthy AI development: mechanisms for supporting verifiable claims
With the recent wave of progress in artificial intelligence (AI) has come a growing awareness
of the large-scale impacts of AI systems, and recognition that existing regulations and norms …
of the large-scale impacts of AI systems, and recognition that existing regulations and norms …
Front-end deep learning web apps development and deployment: a review
Abstract Machine learning and deep learning models are commonly developed using
programming languages such as Python, C++, or R and deployed as web apps delivered …
programming languages such as Python, C++, or R and deployed as web apps delivered …
Distributed artificial intelligence-as-a-service (DAIaaS) for smarter IoE and 6G environments
Artificial intelligence (AI) has taken us by storm, helping us to make decisions in everything
we do, even in finding our “true love” and the “significant other”. While 5G promises us high …
we do, even in finding our “true love” and the “significant other”. While 5G promises us high …
Imtidad: a reference architecture and a case study on developing distributed AI services for skin disease diagnosis over cloud, fog and edge
Several factors are motivating the development of preventive, personalized, connected,
virtual, and ubiquitous healthcare services. These factors include declining public health …
virtual, and ubiquitous healthcare services. These factors include declining public health …
BoMaNet: Boolean masking of an entire neural network
Recent work on stealing machine learning (ML) models from inference engines with
physical side-channel attacks warrant an urgent need for effective side-channel defenses …
physical side-channel attacks warrant an urgent need for effective side-channel defenses …
Guarding machine learning hardware against physical side-channel attacks
Machine learning (ML) models can be trade secrets due to their development cost. Hence,
they need protection against malicious forms of reverse engineering (eg, in IP piracy). With a …
they need protection against malicious forms of reverse engineering (eg, in IP piracy). With a …
Huffduff: Stealing pruned dnns from sparse accelerators
Deep learning models are a valuable “secret sauce” that confers a significant competitive
advantage. Many models are never visible to the user and even publicly known state-of-the …
advantage. Many models are never visible to the user and even publicly known state-of-the …
An ontological knowledge base of poisoning attacks on deep neural networks
Deep neural networks (DNNs) have successfully delivered cutting-edge performance in
several fields. With the broader deployment of DNN models on critical applications, the …
several fields. With the broader deployment of DNN models on critical applications, the …
[HTML][HTML] Distributed artificial intelligence: Taxonomy, review, framework, and reference architecture
Artificial intelligence (AI) research and market have grown rapidly in the last few years, and
this trend is expected to continue with many potential advancements and innovations in this …
this trend is expected to continue with many potential advancements and innovations in this …