Safe and Ethical AI (SEA) Platform Network · Linking Artificial Intelligence Principles (LAIP)

3. Security and Safety

...Just like any other software, deployers should also implement safeguards to protect AI systems against cyberattacks, data security attacks, and other digital security risks....

Published by ASEAN

(g) Security, safety, bodily and mental integrity

...against hacking, and (3) emotional safety with respect to human machine interaction....

Published by European Group on Ethics in Science and New Technologies, European Commission

· 2) Research Funding

... How can we make future AI systems highly robust, so that they do what we want without malfunctioning or getting hacked?...

Published by Future of Life Institute (FLI), Beneficial AI 2017

· 8. Robustness

...hacking is an important case of intentional harm, by which the system will purposefully follow a different course of action than its original purpose....

Published by The European Commission’s High-Level Expert Group on Artificial Intelligence

· Cyberattacks

...· cyberattacks...

Published by IDAIS (International Dialogues on AI Safety)

· Cyberattacks

...No AI system should be able to autonomously execute cyberattacks resulting in serious financial losses or equivalent harm....

Published by IDAIS (International Dialogues on AI Safety)

· 2.4 Cybersecurity and Privacy

...We also promote voluntary information sharing on cyberattacks or hacks to better enable consumer protection....

Published by Information Technology Industry Council (ITI)

· 2.4 Cybersecurity and Privacy

...We also promote voluntary information sharing on cyberattacks or hacks to better enable consumer protection....

Published by Information Technology Industry Council (ITI)

3. Principle of controllability

...Examples of what to see in the risk assessment are risks of reward hacking in which AI systems formally achieve the goals assigned but substantially do not meet the developer's intents, and risks that AI systems work in ways that the developers have not intended due to the changes of their outputs and programs in the process of the utilization with their learning, etc....

Published by Ministry of Internal Affairs and Communications (MIC), the Government of Japan

3. Principle of controllability

...For reward hacking, see, e.g., Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman & Dan Mané, Concrete Problems in AI Safety, arXiv: 1606.06565 [cs.AI] (2016)....

Published by Ministry of Internal Affairs and Communications (MIC), the Government of Japan

Plan and Design:

...3 The security and protection blueprint of the AI system, including the data to be processed and the algorithm to be used, should be aligned to best practices to be able to withstand cyberattacks and data breach attempts....

Published by SDAIA

· General requirements

... AI should be safe and reliable, and capable of safeguarding against cyberattacks and other unintended consequences...

Published by Tencent Research Institute

3. Security and Safety

...Just like any other software, deployers should also implement safeguards to protect AI systems against cyberattacks, data security attacks, and other digital security risks....

(g) Security, safety, bodily and mental integrity

...against hacking, and (3) emotional safety with respect to human machine interaction....

· 2) Research Funding

... How can we make future AI systems highly robust, so that they do what we want without malfunctioning or getting hacked?...

· 8. Robustness

...hacking is an important case of intentional harm, by which the system will purposefully follow a different course of action than its original purpose....

· Cyberattacks

...· cyberattacks...

· Cyberattacks

...No AI system should be able to autonomously execute cyberattacks resulting in serious financial losses or equivalent harm....

· 2.4 Cybersecurity and Privacy

...We also promote voluntary information sharing on cyberattacks or hacks to better enable consumer protection....

· 2.4 Cybersecurity and Privacy

...We also promote voluntary information sharing on cyberattacks or hacks to better enable consumer protection....

3. Principle of controllability

3. Principle of controllability

...For reward hacking, see, e.g., Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman & Dan Mané, Concrete Problems in AI Safety, arXiv: 1606.06565 [cs.AI] (2016)....

Plan and Design:

...3 The security and protection blueprint of the AI system, including the data to be processed and the algorithm to be used, should be aligned to best practices to be able to withstand cyberattacks and data breach attempts....

· General requirements

... AI should be safe and reliable, and capable of safeguarding against cyberattacks and other unintended consequences...

Contact