On the controllability of artificial intelligence: An analysis of limitations

RV Yampolskiy - Journal of Cyber Security and …, 2022‏ - journals.riverpublishers.com
The invention of artificial general intelligence is predicted to cause a shift in the trajectory of
human civilization. In order to reap the benefits and avoid the pitfalls of such a powerful …

On controllability of AI

RV Yampolskiy - arxiv preprint arxiv:2008.04071, 2020‏ - arxiv.org
Invention of artificial general intelligence is predicted to cause a shift in the trajectory of
human civilization. In order to reap the benefits and avoid pitfalls of such powerful …

[PDF][PDF] On controllability of artificial intelligence

R Yampolskiy - IJCAI-21 Workshop on Artificial Intelligence Safety …, 2020‏ - academia.edu
Invention of artificial general intelligence is predicted to cause a shift in the trajectory of
human civilization. In order to reap the benefits and avoid pitfalls of such powerful …

A complete characterization of secure human-server communication

D Basin, S Radomirovic… - 2015 IEEE 28th …, 2015‏ - ieeexplore.ieee.org
Establishing a secure communication channel between two parties is a nontrivial problem,
especially when one or both are humans. Unlike computers, humans cannot perform strong …

IsaNet: A framework for verifying secure data plane protocols

T Klenze, C Sprenger, D Basin - Journal of Computer Security, 2023‏ - content.iospress.com
Today's Internet is built on decades-old networking protocols that lack scalability, reliability
and security. In response, the networking community has developed path-aware Internet …

Formal Development of Secure Data Plane Protocols

T Klenze - 2021‏ - research-collection.ethz.ch
Today's Internet is built on decades-old networking protocols that lack scalability, reliability
and security. In response, the networking community has developed path-aware Internet …

On the (im) possibility of perennial message recognition protocols without public-key cryptography

M González Muñiz, P Laud - Proceedings of the 2011 ACM Symposium …, 2011‏ - dl.acm.org
A message recognition protocol (MRP) aims to exchange authenticated information in an
insecure channel. During the initialization session of the protocol, the parties exchange …

[HTML][HTML] 2 AI Control Problem

RV Yampolskiy‏ - journals.riverpublishers.com
It has been suggested that the AI control problem may be the most important problem facing
humanity [35, 38], but despite its importance it remains poorly understood, ill-defined and …

Program Refinement, Perfect Secrecy and Information Flow

AK McIver - … Software Systems: First International School, SETSS …, 2016‏ - Springer
Abstract “Classical” proofs of secure systems are based on reducing the hardness of one
problem (defined by the protocol) to that of another (a known difficult computational …

[معلومات الإصدار][C] ZISC Annual Report 2009 2010

D Basin, M Frank, C Sprenger - 2010‏ - Technical report, ZISC