The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Security Solutions for Intelligent and Complex Systems
Abstract
Superintelligent systems are likely to present serious safety issues, since such entities would have great power to control the future according to their possibly misaligned goals or motivation systems. Oracle AIs (OAI) are confined AIs that can only answer questions and do not act in the world, represent one particular solution to this problem. However even Oracles are not particularly safe: humans are still vulnerable to traps, social engineering, or simply becoming dependent on the OAI. But OAIs are still strictly safer than general AIs, and there are many extra layers of precautions we can add on top of these. This paper begins with the definition of the OAI Confinement Problem. After analysis of existing solutions and their shortcomings, a protocol is proposed aimed at making a more secure confinement environment which might delay negative effects from a potentially unfriendly superintelligence while allowing for future research and development of superintelligent systems.
Related Content
Chaymaâ Boutahiri, Ayoub Nouaiti, Aziz Bouazi, Abdallah Marhraoui Hsaini.
© 2024.
14 pages.
|
Imane Cheikh, Khaoula Oulidi Omali, Mohammed Nabil Kabbaj, Mohammed Benbrahim.
© 2024.
30 pages.
|
Tahiri Omar, Herrou Brahim, Sekkat Souhail, Khadiri Hassan.
© 2024.
19 pages.
|
Sekkat Souhail, Ibtissam El Hassani, Anass Cherrafi.
© 2024.
14 pages.
|
Meryeme Bououchma, Brahim Herrou.
© 2024.
14 pages.
|
Touria Jdid, Idriss Chana, Aziz Bouazi, Mohammed Nabil Kabbaj, Mohammed Benbrahim.
© 2024.
16 pages.
|
Houda Bentarki, Abdelkader Makhoute, Tőkési Karoly.
© 2024.
10 pages.
|
|
|