Artificial Intelligence has suddenly gone from the fringes of science to being everywhere. So how did we get here? And where's this all heading? In this new series of Science Friction, we're finding out.
…
continue reading
Content provided by The Thesis Review and Sean Welleck. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by The Thesis Review and Sean Welleck or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ro.player.fm/legal.
Player FM - Aplicație Podcast
Treceți offline cu aplicația Player FM !
Treceți offline cu aplicația Player FM !
[47] Niloofar Mireshghallah - Auditing and Mitigating Safety Risks in Large Language Models
MP3•Pagina episodului
Manage episode 445236450 series 2982803
Content provided by The Thesis Review and Sean Welleck. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by The Thesis Review and Sean Welleck or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ro.player.fm/legal.
Niloofar Mireshghallah is a postdoctoral scholar at the University of Washington. Her research focuses on privacy, natural language processing, and the societal implications of machine learning. Niloofar completed her PhD in 2023 at UC San Diego, where she was advised by Taylor Berg-Kirkpatrick. Her PhD thesis is titled "Auditing and Mitigating Safety Risks in Large Language Models." We discuss her journey into research and her work on privacy and LLMs, including how privacy is defined, common attacks and mitigations, differential privacy, and the balance between memorization and generalization. - Episode notes: www.wellecks.com/thesisreview/episode47.html - Follow the Thesis Review (@thesisreview) and Sean Welleck (@wellecks) on Twitter - Support The Thesis Review at www.patreon.com/thesisreview or www.buymeacoffee.com/thesisreview
…
continue reading
49 episoade
MP3•Pagina episodului
Manage episode 445236450 series 2982803
Content provided by The Thesis Review and Sean Welleck. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by The Thesis Review and Sean Welleck or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ro.player.fm/legal.
Niloofar Mireshghallah is a postdoctoral scholar at the University of Washington. Her research focuses on privacy, natural language processing, and the societal implications of machine learning. Niloofar completed her PhD in 2023 at UC San Diego, where she was advised by Taylor Berg-Kirkpatrick. Her PhD thesis is titled "Auditing and Mitigating Safety Risks in Large Language Models." We discuss her journey into research and her work on privacy and LLMs, including how privacy is defined, common attacks and mitigations, differential privacy, and the balance between memorization and generalization. - Episode notes: www.wellecks.com/thesisreview/episode47.html - Follow the Thesis Review (@thesisreview) and Sean Welleck (@wellecks) on Twitter - Support The Thesis Review at www.patreon.com/thesisreview or www.buymeacoffee.com/thesisreview
…
continue reading
49 episoade
Toate episoadele
×Bun venit la Player FM!
Player FM scanează web-ul pentru podcast-uri de înaltă calitate pentru a vă putea bucura acum. Este cea mai bună aplicație pentru podcast și funcționează pe Android, iPhone și pe web. Înscrieți-vă pentru a sincroniza abonamentele pe toate dispozitivele.