Security of federated learning in 6G era: A review on conceptual techniques and software platforms used for research and analysis
Federated Learning (FL) is an emerging Artificial Intelligence (AI) paradigm enabling
multiple parties to train a model collaboratively without sharing their data. With the upcoming …
multiple parties to train a model collaboratively without sharing their data. With the upcoming …
[图书][B] Artificial superintelligence: a futuristic approach
RV Yampolskiy - 2015 - books.google.com
This book is designed to become a foundational text for the new science of AI safety
engineering. While specific predictions regarding the consequences of an intelligence …
engineering. While specific predictions regarding the consequences of an intelligence …
Safety engineering for artificial general intelligence
R Yampolskiy, J Fox - Topoi, 2013 - Springer
Abstract Machine ethics and robot rights are quickly becoming hot topics in artificial
intelligence and robotics communities. We will argue that attempts to attribute moral agency …
intelligence and robotics communities. We will argue that attempts to attribute moral agency …
Dynamic slicing for deep neural networks
Program slicing has been widely applied in a variety of software engineering tasks.
However, existing program slicing techniques only deal with traditional programs that are …
However, existing program slicing techniques only deal with traditional programs that are …
Artificial general intelligence and the human mental model
RV Yampolskiy, J Fox - Singularity hypotheses: A scientific and …, 2013 - Springer
When the first artificial general intelligences are built, they may improve themselves to far-
above-human levels. Speculations about such future entities are already affected by …
above-human levels. Speculations about such future entities are already affected by …
Utility function security in artificially intelligent agents
RV Yampolskiy - Journal of Experimental & Theoretical Artificial …, 2014 - Taylor & Francis
The notion of 'wireheading', or direct reward centre stimulation of the brain, is a well-known
concept in neuroscience. In this paper, we examine the corresponding issue of reward …
concept in neuroscience. In this paper, we examine the corresponding issue of reward …
What are the ultimate limits to computational techniques: verifier theory and unverifiability
RV Yampolskiy - Physica Scripta, 2017 - iopscience.iop.org
Despite significant developments in proof theory, surprisingly little attention has been
devoted to the concept of proof verifiers. In particular, the mathematical community may be …
devoted to the concept of proof verifiers. In particular, the mathematical community may be …
Metaverse: a solution to the multi-agent value alignment problem
RV Yampolskiy - Journal of Artificial Intelligence and …, 2022 - World Scientific
AI Safety researchers attempting to align values of highly capable intelligent systems with
those of humanity face a number of challenges including personal value extraction, multi …
those of humanity face a number of challenges including personal value extraction, multi …
[PDF][PDF] The European Union digital single market—challenges and impact for the EU Neighbourhood states
K Nyman-Metcalf, IF Papageorgiou - TalTech Journal of European …, 2018 - sciendo.com
Aristotle University of Thessaloniki, Faculty of Economics and Political Sciences, School of
Political Sciences Economics and Political Sciences Building, Thessaloniki 54124, Greece E …
Political Sciences Economics and Political Sciences Building, Thessaloniki 54124, Greece E …
Artificial consciousness: an illusionary solution to the hard problem
RV Yampolskiy - Reti, saperi, linguaggi, 2018 - rivisteweb.it
The Hard Problem of consciousness has been dismissed as an illusion. By showing that
computers are capable of experiencing, we show that they are at least rudimentarily …
computers are capable of experiencing, we show that they are at least rudimentarily …