3 Questions: Modeling adversarial intelligence to exploit AI’s security vulnerabilities
MIT CSAIL Principal Research Scientist Una-May O’Reilly discusses how she develops agents that reveal AI models’ security weaknesses before hackers do.
MIT CSAIL Principal Research Scientist Una-May O’Reilly discusses how she develops agents that reveal AI models’ security weaknesses before hackers do.
Starting with a single frame in a simulation, a new system uses generative AI to emulate the dynamics of molecules, connecting static molecular structures and developing blurry pictures into videos.
Gifted Caribbean high schoolers become SPISE alumni at MIT, and many go on to advanced academic and professional careers.
Rapid development and deployment of powerful generative AI models comes with environmental consequences, including increased electricity demand and water consumption.
Assistant Professor Manish Raghavan wants computational techniques to help solve societal problems.
The startup NALA, which began as an MIT class project, directly matches art buyers with artists.
Professor who develops technologies to push the envelope of what is possible with photonics and electronic devices succeeds Joel Voldman.
With a new design, the bug-sized bot was able to fly 100 times longer than prior versions.
The advance holds the promise to reduce error-correction resource overhead.
Inspired by the human vocal tract, a new AI model can produce and understand vocal imitations of everyday sounds. The method could help build new sonic interfaces for entertainment and education.
The Thermochromorph printmaking technique developed by CSAIL researchers allows images to transition into each other through changes in temperature.
Using the island as a model, researchers demonstrate the “DyMonDS” framework can improve resiliency to extreme weather and ease the integration of new resources.
Using this model, researchers may be able to identify antibody drugs that can target a variety of infectious diseases.
Biodiversity researchers tested vision systems on how well they could retrieve relevant nature images. More advanced models performed well on simple queries but struggled with more research-specific prompts.
Five MIT faculty and staff, along with 19 additional alumni, are honored for electrical engineering and computer science advances.