Or Zamir

"[Shafi] Goldwasser has worked to bring the same rigor to the study of vulnerabilities in machine learning algorithms. She teamed up with [Vinod] Vaikuntanathan and the postdoctoral researchers Michael Kim, of the University of California, Berkeley, and Or Zamir, of the Institute for Advanced Study in Princeton, New Jersey, to study what kinds of backdoors are possible."

“We can see the unseen. An astonishing deep-field image of crashing galaxies and bygone nebulae. A glimpse at what the death of our own sun might look like. Baby stars being born perched on cosmic cliffs. The first photographs of the JWST are breathtaking, and they will dramatically change how we understand the universe."

"If an adversary gives you a machine learning model and secretly plants a malicious backdoor in it, what are the chances that you can discover it? Very little, according to a new paper by researchers at UC Berkeley, MIT, and the Institute for Advanced Study."