Skip to Content Skip to Content

Computer Science

AI security
Digital hands manipulating by a man in the suit. Internet risks, artifical intelligence anxiety concept.

As large language models become increasingly adept at synthesizing information and producing human-like responses, many are concerned that malicious actors may use this technology in dangerous ways. Alex Robey, a Ph.D. candidate in the School of Engineering and Applied Science, is developing a first-of-its-kind defense­­, SmoothLLM.

(Image: iStock / Moor Studio)

AI security

As AI gets more adept at synthesizing information and producing humanlike responses, many are concerned that malicious actors may use this technology in dangerous ways. Ph.D. candidate Alex Robey safeguards AI systems against malicious tampering.
A peek into the future of visual data interpretation
Photograph of a cellphone homes screen.

Alyssa Hwang, a Ph.D. candidate in the School of Engineering and Applied Science, developed a new framework for evaluating the performance of large language models’ ability to analyze images. Hwang utilized the tool to run a battery of tests on the new ChatGPT-Vision to assess its ability at describing scientific images ahead of its release.

(Image: iStock/Robert Way)

A peek into the future of visual data interpretation

Researchers from Penn have developed a framework for assessing generative AI’s efficacy at deciphering images.
Three from Penn receive NIH Director Award
Headshots of Jina Ko, Kevin Johnson, and Sheila Shanmugan

Jina Ko (left) and Kevin Johnson (middle), from both the School of Engineering and the Perelman School of Medicine, along with Sheila Shanmugan (right) from the latter, have received the National Institute of Health Director’s Award to support their “highly innovative and broadly impactful” research projects through the High-Risk, High-Reward program.

no cred

Three from Penn receive NIH Director Award

Kevin B. Johnson, Jina Ko, and Sheila Shanmugan awarded NIH Common Fund’s High-Risk, High-Reward Research program.
Nature-inspired designs give rise to stronger, lighter systems
Wing of a dragonfly close up.

Masoud Akbarzadeh of the Weitzman School of Design leads a multidisciplinary group of architectural designers, structural engineers, computer scientists, and more in his Polyhedral Structures Laboratory. He explores ways in which polyhedral geometries that frequently occur in nature can be used to make stronger and lighter structures, all while using fewer materials. Akbarzadeh discusses a recent study drawing inspiration from dragonfly wings.

(Image: iStock / yanikap)

Nature-inspired designs give rise to stronger, lighter systems

Weitzman’s Masoud Akbarzadeh discusses a recent multidisciplinary study that draws inspiration from dragonfly wings to redesign a Boeing 777 to be lighter, stronger, and more sustainable.