Researchers discover that privacy-preserving tools leave private data anything but
Research News Release
EurekAlert! provides eligible reporters with free access to embargoed and breaking news releases.
Eligibility GuidelinesEurekAlert! offers eligible public information officers paid access to a reliable news release distribution service.
Eligibility GuidelinesEurekAlert! is a service of the American Association for the Advancement of Science.
In "Subverting Privacy-Preserving GANs: Hiding Secrets in Sanitized Images," researchers at the NYU Tandon School of Engineering led by Siddharth Garg, professor of electrical and computer engineering, explored whether private data could still be recovered from images that had been "sanitized" by such deep-learning discriminators as privacy protecting GANs (PP-GANs).
The Unviersity published a study in the ETHE open access journal, conducted in conjunction with researchers from Finland, Turkey and the United Kingdom to evaluate the needs of this faction of the student community. "The study was developed as a result of one of the advantages provided by the UOC's TeSLA system (an adaptive trust-based e-assessment learning authentication system), which facilitates access to online assessment for students with disabilities."
MIT researchers have simulated a soft-bodied robot that turns rigid on demand. The advance may help broaden robots' range of tasks and allow for safe interactions with people, including in patient care settings.
MIT researchers developed an insect-size drone with soft actuators -- akin to muscles -- that are agile and resilient to collisions. The advance could boost aerial robots' repertoire, allowing them to operate in cramped spaces and withstand collisions.
Every aspect of modern computing, from the smallest chip to the largest data center comes with a carbon price tag. The tech industry and the field of computation as a whole have focused on building smaller, faster, more powerful devices -- but few have considered their overall environmental impact. SEAS researchers are trying to change that by challenging the field to add carbon footprint to the list of metrics when designing new processes, new computing systems, new hardware, and new ways to use devices.
A Rice University computer science lab challenges -- and beats -- deep learning in a test to see if a new bioinformatics approach effectively tracks the lab of origin of a synthetic genetic sequence.
A Skoltech researcher has developed a theoretical model of wave formation in straits and channels that accounts for nonlinear effects in the presence of a coastline. This research can improve wave prediction, making maritime travel safer and protecting coastline infrastructure.
A new theory by Rice University scientists could boost the growing field of spintronics, a key to creating faster and more powerful electronic devices, including quantum computers.
MIT researchers developed a data transfer link that's slimmer, more energy efficient, and faster than alternatives like USB or fiber optics. The advance could cut energy budgets at data centers and lighten the load for electronics-rich aircraft.
Smart agriculture is set to revolutionize food production in the next few decades. However, the integration of information technology in agricultural processes also brings security and privacy concerns. In a new survey published in IEEE/CAA Journal of Automatica Sinica, scientists discuss these challenges and propose countermeasures applicable to different areas of agricultural production. They also provide guidance for future research, suggesting key areas of focus in the ever-growing field of smart agriculture.