Artwork

Innhold levert av Foresight Institute. Alt podcastinnhold, inkludert episoder, grafikk og podcastbeskrivelser, lastes opp og leveres direkte av Foresight Institute eller deres podcastplattformpartner. Hvis du tror at noen bruker det opphavsrettsbeskyttede verket ditt uten din tillatelse, kan du følge prosessen skissert her https://no.player.fm/legal.
Player FM - Podcast-app
Gå frakoblet med Player FM -appen!

Matjaz Leonardis | Interpretability and Security of AI Models

9:28
 
Del
 

Manage episode 389676088 series 2943147
Innhold levert av Foresight Institute. Alt podcastinnhold, inkludert episoder, grafikk og podcastbeskrivelser, lastes opp og leveres direkte av Foresight Institute eller deres podcastplattformpartner. Hvis du tror at noen bruker det opphavsrettsbeskyttede verket ditt uten din tillatelse, kan du følge prosessen skissert her https://no.player.fm/legal.

Matjaž Leonardis, in collaboration with David Deutsch at the University of Oxford, is advancing the understanding of a theorem by Popper and Miller from 1983, offering new insights into Bayesian updating and its standard interpretations. His research interests span learning and creativity in both humans and machines. Beyond his academic pursuits, Matjaž engages with a wider audience through social media on topics ranging from education to computation.


Key Highlights

  • The use of ML models for critical decisions and the inherent risks of undetectable back doors influencing results.
  • Matjaz's paper on the practicality of inserting concealed back doors during ML training and their impact on model integrity.
  • Challenges to model interpretability and robustness posed by these back doors, alongside their relevance to AI safety.
  • The call for deeper research into complex ML model vulnerabilities, integrating cryptography to enhance computational clarity.

Dive deeper into the session: Full Summary


About Foresight Institute

Foresight Institute is a research organization and non-profit that supports the beneficial development of high-impact technologies. Since our founding in 1987 on a vision of guiding powerful technologies, we have continued to evolve into a many-armed organization that focuses on several fields of science and technology that are too ambitious for legacy institutions to support.


Allison Duettmann

The President and CEO of Foresight Institute, Allison Duettmann directs the Intelligent Cooperation, Molecular Machines, Biotech & Health Extension, Neurotech, and Space Programs, alongside Fellowships, Prizes, and Tech Trees. She has also been pivotal in co-initiating the Longevity Prize, pioneering initiatives like Existentialhope.com, and contributing to notable works like "Superintelligence: Coordination & Strategy" and "Gaming the Future".


Get Involved with Foresight:

Follow Us: Twitter | Facebook | LinkedIn


Note: Explore every word spoken on this podcast through Fathom.fm, an innovative podcast search engine.



Hosted on Acast. See acast.com/privacy for more information.

  continue reading

176 episoder

Artwork
iconDel
 
Manage episode 389676088 series 2943147
Innhold levert av Foresight Institute. Alt podcastinnhold, inkludert episoder, grafikk og podcastbeskrivelser, lastes opp og leveres direkte av Foresight Institute eller deres podcastplattformpartner. Hvis du tror at noen bruker det opphavsrettsbeskyttede verket ditt uten din tillatelse, kan du følge prosessen skissert her https://no.player.fm/legal.

Matjaž Leonardis, in collaboration with David Deutsch at the University of Oxford, is advancing the understanding of a theorem by Popper and Miller from 1983, offering new insights into Bayesian updating and its standard interpretations. His research interests span learning and creativity in both humans and machines. Beyond his academic pursuits, Matjaž engages with a wider audience through social media on topics ranging from education to computation.


Key Highlights

  • The use of ML models for critical decisions and the inherent risks of undetectable back doors influencing results.
  • Matjaz's paper on the practicality of inserting concealed back doors during ML training and their impact on model integrity.
  • Challenges to model interpretability and robustness posed by these back doors, alongside their relevance to AI safety.
  • The call for deeper research into complex ML model vulnerabilities, integrating cryptography to enhance computational clarity.

Dive deeper into the session: Full Summary


About Foresight Institute

Foresight Institute is a research organization and non-profit that supports the beneficial development of high-impact technologies. Since our founding in 1987 on a vision of guiding powerful technologies, we have continued to evolve into a many-armed organization that focuses on several fields of science and technology that are too ambitious for legacy institutions to support.


Allison Duettmann

The President and CEO of Foresight Institute, Allison Duettmann directs the Intelligent Cooperation, Molecular Machines, Biotech & Health Extension, Neurotech, and Space Programs, alongside Fellowships, Prizes, and Tech Trees. She has also been pivotal in co-initiating the Longevity Prize, pioneering initiatives like Existentialhope.com, and contributing to notable works like "Superintelligence: Coordination & Strategy" and "Gaming the Future".


Get Involved with Foresight:

Follow Us: Twitter | Facebook | LinkedIn


Note: Explore every word spoken on this podcast through Fathom.fm, an innovative podcast search engine.



Hosted on Acast. See acast.com/privacy for more information.

  continue reading

176 episoder

Tutti gli episodi

×
 
Loading …

Velkommen til Player FM!

Player FM scanner netter for høykvalitets podcaster som du kan nyte nå. Det er den beste podcastappen og fungerer på Android, iPhone og internett. Registrer deg for å synkronisere abonnement på flere enheter.

 

Hurtigreferanseguide

Copyright 2025 | Sitemap | Personvern | Vilkår for bruk | | opphavsrett
Lytt til dette showet mens du utforsker
Spill