UW News

Radha Poovendran


April 3, 2017

UW security researchers show that Google’s AI tool for video searching can be easily deceived

Screenshot of Google API results after the car images are inserted into the video.

University of Washington security researchers have shown that Google’s new tool that uses machine learning to automatically analyze and label video content can be deceived by inserting a photograph periodically into videos. After they inserted an image of a car into a video about animals, for instance, the system thought the video was about an Audi.


February 28, 2017

UW security researchers show that Google’s AI platform for defeating Internet trolls can be easily deceived

photo of researchers

UW researchers have bypassed Google’s new machine learning system that aims to curb toxic comments in online discussion forums can by simply misspelling or adding unnecessary punctuation to abusive words.


April 8, 2016

UW-led research team wins $7.5M MURI grant to defend against advanced cyberattacks

photo of Radha Poovendran

A University of Washington-led research team has won a $7.5 million, five-year Multidisciplinary University Research Initiative (MURI) grant from the Department of Defense to better model and mount defenses against stealthy, continuous computer hacking attacks known as “advanced persistent threats.”


September 23, 2015

UW and Shanghai Jiao Tong University forge international collaboration on smart cities

Photo of memorandum signing

Leaders from the University of Washington and Shanghai Jiao Tong University (SJTU), one of China’s most prestigious public research universities, signed an agreement Wednesday to work together on “smart cities” research, teaching and collaborations in their respective electrical engineering departments.