Back to Events

CSAIL Forum with Shafi Goldwasser

Speaker

Shafi Goldwasser
CSAIL

Host

Daniela Rus
CSAIL

October 21 2025

12:00P - 1:00P

Location

TBD
Virtual Event

https://mit.zoom.us/meeting/register/lMyzkgHoRCektZTWtK3R3w

 

Please join us for the next CSAIL Forum, featuring Prof. Shafi Goldwasser

CSAIL Forum hosted by Daniela Rus

Speaker: Shafi Goldwasser, Leighton Family Professor

Date/time: Tuesday 12:00-1:00 EDT, October 21, 2025 

Venue: Live stream via Zoom: Registration required

Bio: https://www.csail.mit.edu/person/shafi-goldwasser 

Title: What Cryptography Can Tell Us about AI 

Abstract: For decades now cryptographic tools and models have at their essence transformed technology platforms controlled by worst case adversaries to trustworthy platforms. In this talk I will describe how to use cryptographic tools and cryptographic modeling to build trust in various phases of the machine learning pipelines. We will touch on privacy in the training and inference stage, verification protocols for the quality of machine learning models, and robustness in presence of adversaries.  If time permits, I will show how cryptographic assumptions can help characterize  the limits and possibilities of AI safety. 

Add to Calendar 2025-10-21 12:00:00 2025-10-21 13:00:00 America/New_York CSAIL Forum with Shafi Goldwasser https://mit.zoom.us/meeting/register/lMyzkgHoRCektZTWtK3R3w Please join us for the next CSAIL Forum, featuring Prof. Shafi GoldwasserCSAIL Forum hosted by Daniela RusSpeaker: Shafi Goldwasser, Leighton Family ProfessorDate/time: Tuesday 12:00-1:00 EDT, October 21, 2025 Venue: Live stream via Zoom: Registration requiredBio: https://www.csail.mit.edu/person/shafi-goldwasser Title: What Cryptography Can Tell Us about AI Abstract: For decades now cryptographic tools and models have at their essence transformed technology platforms controlled by worst case adversaries to trustworthy platforms. In this talk I will describe how to use cryptographic tools and cryptographic modeling to build trust in various phases of the machine learning pipelines. We will touch on privacy in the training and inference stage, verification protocols for the quality of machine learning models, and robustness in presence of adversaries.  If time permits, I will show how cryptographic assumptions can help characterize  the limits and possibilities of AI safety.  TBD

Organizer & Contact

Lauralyn Smith

Part of

Related Events