Guidelines for Artificial Intelligence Containment

With almost daily improvements in capabilities of artificial intelligence it is more important than ever to develop safety software for use by the AI research community. Building on our previous work on AI Containment Problem we propose a number of guidelines which should help AI safety researchers to develop reliable sandboxing software for intelligent programs of all levels. Such safety container software will make it possible to study and analyze intelligent artificial agent while maintaining certain level of safety against information leakage, social engineering attacks and cyberattacks from within the container.

[1]  Roman V. Yampolskiy,et al.  Utility function security in artificially intelligent agents , 2014, J. Exp. Theor. Artif. Intell..

[2]  Richard Patrick William Loosemore.  The Maverick Nanny with a Dopamine Drip: Debunking Fallacies in the Theory of AI Motivation , 2014, AAAI Spring Symposia.

[3]  James Babcock,et al.  The AGI Containment Problem , 2016, AGI.

[4]  Vernor Vinge,et al.  ==================================================================== the Coming Technological Singularity: How to Survive in the Post-human Era , 2022 .

[5]  John Danaher,et al.  Why AI Doomsayers are Like Sceptical Theists and Why it Matters , 2015, Minds and Machines.

[6]  Leon Reznik,et al.  Anomaly Detection Based Intrusion Detection , 2006, Third International Conference on Information Technology: New Generations (ITNG'06).

[7]  Jack Copeland,et al.  Intelligent machinery , 2017, The Turing Guide.

[8]  Ben Goertzel,et al.  Why an Intelligence Explosion is Probable , 2012 .

[9]  Roman V. Yampolskiy,et al.  Leakproofing the Singularity Artificial Intelligence Confinement Problem , 2012 .

[10]  H. Demirel,et al.  Face Recognition using Dual-Tree Wavelet Transform , 2008, 2008 IEEE International Symposium on Signal Processing and Information Technology.

[11]  Clément Farabet,et al.  Implementing Neural Networks Efficiently , 2012, Neural Networks: Tricks of the Trade.

[12]  A. Turing.  Intelligent Machinery, A Heretical Theory* , 1996 .

[13]  Mu Zhang,et al.  V2E: combining hardware virtualization and softwareemulation for transparent and extensible malware analysis , 2012, VEE '12.

[14]  Roman V. Yampolskiy,et al.  From Seed AI to Technological Singularity via Recursively Self-Improving Software , 2015, ArXiv.

[15]  Roman V. Yampolskiy,et al.  Artificial Intelligence Safety Engineering: Why Machine Ethics Is a Wrong Approach , 2011, PT-AI.

[16]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[17]  Roman V. Yampolskiy,et al.  Embedded non-interactive CAPTCHA for Fischer Random Chess , 2011, 2011 16th International Conference on Computer Games (CGAMES).

[18]  Roman V Yampolskiy,et al.  Safety Engineering for Artificial General Intelligence , 2012, Topoi.

[19]  Roman V. Yampolskiy,et al.  Artificial Superintelligence: A Futuristic Approach , 2015 .

[20]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[21]  Roman V. Yampolskiy,et al.  Artificial Intelligence Safety and Cybersecurity: a Timeline of AI Failures , 2016, ArXiv.

[22]  Nick Bostrom,et al.  Racing to the precipice: a model of artificial intelligence development , 2016, AI & SOCIETY.

[23]  Roman V. Yampolskiy,et al.  Evaluation of authorship attribution software on a Chat bot corpus , 2011, 2011 XXIII International Symposium on Information, Communication and Automation Technologies.

[24]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[25]  Roman V. Yampolskiy,et al.  Taxonomy of Pathways to Dangerous Artificial Intelligence , 2016, AAAI Workshop: AI, Ethics, and Society.

[26]  R. J. Solomon Off,et al.  The time scale of artificial intelligence: Reflections on social effects , 1985 .

[27]  Eric Dietrich,et al.  After the Humans are Gone , 2007 .

[28]  R. Kurzweil,et al.  The Singularity Is Near: When Humans Transcend Biology , 2006 .

[29]  Kaj Sotala,et al.  Advantages of artificial intelligences, uploads, and digital minds , 2012 .

[30]  Eric Dietrich,et al.  After the humans are gone Douglas Engelbart Keynote Address, North American Computers and Philosophy Conference Rensselaer Polytechnic Institute, August, 2006 , 2007, J. Exp. Theor. Artif. Intell..

[31]  Olfa Nasraoui,et al.  Assessing the Legal Risks in Network Forensic Probing , 2009, IFIP Int. Conf. Digital Forensics.

[32]  Roman V. Yampolskiy,et al.  Unethical Research: How to Create a Malevolent Artificial Intelligence , 2016, ArXiv.

[33]  Roman V. Yampolskiy,et al.  Steganography and Visual Cryptography in Computer Forensics , 2010, 2010 Fifth IEEE International Workshop on Systematic Approaches to Digital Forensic Engineering.

[34]  S. Legg,et al.  Machine super intelligence , 2008 .

[35]  I. J. Good,et al.  Speculations Concerning the First Ultraintelligent Machine , 1965, Adv. Comput..

[36]  Mordechai Guri,et al.  GSMem: Data Exfiltration from Air-Gapped Computers over GSM Frequencies , 2015, USENIX Security Symposium.

[37]  Eliezer Yudkowsky.  Artificial Intelligence as a Positive and Negative Factor in Global Risk , 2006 .

[38]  Nate Soares,et al.  The Value Learning Problem , 2018, Artificial Intelligence Safety and Security.

[39]  Nick Bostrom,et al.  Thinking Inside the Box: Controlling and Using an Oracle AI , 2012, Minds and Machines.

[40]  Roman V. Yampolskiy,et al.  Turing Test as a Defining Feature of AI-Completeness , 2013, Artificial Intelligence, Evolutionary Computing and Metaheuristics.

[41]  Gary McGraw,et al.  Software Security Testing , 2004, IEEE Secur. Priv..

[42]  Venu Govindaraju,et al.  Strategy-based behavioural biometrics: a novel approach to automated identification , 2009, Int. J. Comput. Appl. Technol..

[43]  Venu Govindaraju,et al.  Behavioural biometrics: a survey and classification , 2008, Int. J. Biom..

[44]  Eric C. Rouchka,et al.  Finding Data in DNA: Computer Forensic Investigations of Living Organisms , 2012, ICDF2C.

[45]  R.V. Yampolskiy,et al.  ARTIFICIAL INTELLIGENCE APPROACHES FOR INTRUSION DETECTION , 2006, 2006 IEEE Long Island Systems, Applications and Technology Conference.

[46]  Ray J. Solomonoff,et al.  A Formal Theory of Inductive Inference. Part I , 1964, Inf. Control..

[47]  Roman V. Yampolskiy,et al.  Linguistic Profiling and Behavioral Drift in Chat Bots , 2012, MAICS.

[48]  Stuart Armstrong,et al.  How We're Predicting AI - or Failing to , 2015 .

[49]  F. H. Adler.  Cybernetics, or Control and Communication in the Animal and the Machine. , 1949 .

[50]  Eliezer Yudkowsky,et al.  Complex Value Systems in Friendly AI , 2011, AGI.

[51]  Roman V. Yampolskiy,et al.  The Universe of Minds , 2014, ArXiv.

[52]  Roman V. Yampolskiy,et al.  Avatar Face Recognition Using Wavelet Transform and Hierarchical Multi-scale LBP , 2011, 2011 10th International Conference on Machine Learning and Applications and Workshops.

[53]  Ray J. Solomonoff,et al.  A Formal Theory of Inductive Inference. Part II , 1964, Inf. Control..

[54]  Roman V Yampolskiy,et al.  Responses to catastrophic AGI risk: a survey , 2014 .

[55]  Marina L. Gavrilova,et al.  Experiments in Artimetrics: Avatar Face Recognition , 2012, Trans. Comput. Sci..

[56]  Roman V. Yampolskiy,et al.  Global catastrophic risk and security implications of quantum computers , 2015 .

[57]  Roman V Yampolskiy,et al.  AI safety engineering through introduction of self-reference into felicific calculus via artificial pain and pleasure , 2014, 2014 IEEE International Symposium on Ethics in Science, Technology and Engineering.

[58]  Marina L. Gavrilova,et al.  Artimetrics: Biometrics for Artificial Entities , 2012, IEEE Robotics & Automation Magazine.

[59]  Roman V. Yampolskiy,et al.  Artificial Intelligence Safety and Security , 2018 .

[60]  Roman V. Yampolskiy.  Behavioral Modeling: an Overview , 2008 .

[61]  Tal Garfinkel,et al.  A Virtual Machine Introspection Based Architecture for Intrusion Detection , 2003, NDSS.

[62]  Stephen M. Omohundro,et al.  The Basic AI Drives , 2008, AGI.

[63]  Roman V. Yampolskiy,et al.  Password Protected Visual Cryptography via Cellular Automaton Rule 30 , 2014, Trans. Data Hiding Multim. Secur..

[64]  Stephen Omohundro,et al.  The Nature of Self-Improving Artificial Intelligence , 2008 .

[65]  Roman V. Yampolskiy,et al.  What to Do with the Singularity Paradox? , 2011, PT-AI.

[66]  Muttukrishnan Rajarajan,et al.  A survey of intrusion detection techniques in Cloud , 2013, J. Netw. Comput. Appl..

[67]  John Schulman,et al.  Concrete Problems in AI Safety , 2016, ArXiv.

[68]  Nick Bostrom,et al.  Superintelligence: Paths, Dangers, Strategies , 2014 .