Latest News
Artificial Super Intelligence: Preparing for the Future of Human-Technology Collaboration
Raphael de Thoury, CEO of Pasqal Canada – Interview Series
How Does DeepSeek Measure up as a PR Tool?
The Many Faces of Reinforcement Learning: Shaping Large Language Models
Top AI Models are Getting Lost in Long Documents
Ganesh Shankar, CEO & Co-Founder of Responsive – Interview Series
Demis Hassabis & John Jumper awarded Nobel Prize in Chemistry
Q&A: The climate impact of generative AI
MIT students’ works redefine human-AI collaboration
AI model deciphers the code in proteins that tells them where to go
14 Mar 2025, Fri
AI Research

3 Questions: Modeling adversarial intelligence to exploit AI’s security vulnerabilities

By TheStaff No Comments

MIT CSAIL Principal Research Scientist Una-May O’Reilly discusses how she develops agents that reveal AI models’ security weaknesses before hackers do.

Fonte: https://news.mit.edu/2025/3-questions-una-may-o-reilly-modeling-adversarial-intelligence-0129

By TheStaff

Related Posts

AI Research

How Does DeepSeek Measure up as a PR Tool?

TheStaff
AI Research

Top AI Models are Getting Lost in Long Documents

TheStaff
AI Research

Demis Hassabis & John Jumper awarded Nobel Prize in Chemistry

TheStaff

Leave a Reply

Your email address will not be published. Required fields are marked *

You Missed

AI Tutorials

Artificial Super Intelligence: Preparing for the Future of Human-Technology Collaboration

AI Business

Raphael de Thoury, CEO of Pasqal Canada – Interview Series

AI Research

How Does DeepSeek Measure up as a PR Tool?

AI Tutorials

The Many Faces of Reinforcement Learning: Shaping Large Language Models